Automated PR - 2026-06-17

2026-06-17 14:06:32 +00:00
20 changed files with 5 additions and 5473 deletions
@@ -1,6 +1,6 @@
 [project]
 name = "ltx-core"
-version = "1.1.6"
+version = "v1.1.6"
 description = "Core implementation of Lightricks' LTX-2 model"
 readme = "README.md"
 requires-python = ">=3.10"
@@ -1,6 +1,6 @@
 [project]
 name = "ltx-pipelines"
-version = "1.1.6"
+version = "v1.1.6"
 description = "Pipelines implementation for Lightricks' LTX-2 model"
 readme = "README.md"
 requires-python = ">=3.10"
@@ -1,3 +1,4 @@
 configs/*.yaml
 datasets
 outputs
 wandb
@@ -1,340 +0,0 @@
 # =============================================================================
 # LTX-2 Audio-to-Audio IC-LoRA Training Configuration
 # =============================================================================
 #
 # This configuration is for training In-Context LoRA (IC-LoRA) adapters that
 # enable audio-to-audio transformations. IC-LoRA learns to apply audio
 # transformations (e.g., style transfer, voice conversion, sound effects, etc.)
 # by conditioning on reference audio.
 #
 # Key differences from text-to-video LoRA:
 #   - Uses reference audio as conditioning input alongside text prompts
 #   - Requires preprocessed reference audio latents in addition to target latents
 #   - Audio-only training (no video modality)
 #   - Validation requires reference audio to demonstrate the transformation
 #
 # Dataset structure:
 #   preprocessed_data_root/
 #   ├── conditions/              # Text embeddings for each sample
 #   ├── audio_latents/           # Target audio latents (what the model learns to generate)
 #   └── reference_audio_latents/ # Reference audio latents (conditioning input)
 #
 # Dataset metadata columns: audio, reference_audio, caption
 #
 # =============================================================================
 # -----------------------------------------------------------------------------
 # Model Configuration
 # -----------------------------------------------------------------------------
 # Specifies the base model to fine-tune and the training mode.
 model:
  # Path to the LTX-2 model checkpoint (.safetensors file)
  # This should be a local path to your downloaded model
  model_path: "path/to/ltx-2-model.safetensors"
  # Path to the text encoder model directory
  # For LTX-2, this is typically the Gemma-based text encoder
  text_encoder_path: "path/to/gemma-text-encoder"
  # Training mode: "lora" for efficient adapter training, "full" for full fine-tuning
  training_mode: "lora"
  # Optional: Path to resume training from a checkpoint
  # Can be a checkpoint file (.safetensors) or directory (uses latest checkpoint)
  load_checkpoint: null
 # -----------------------------------------------------------------------------
 # LoRA Configuration
 # -----------------------------------------------------------------------------
 # Controls the Low-Rank Adaptation parameters for efficient fine-tuning.
 lora:
  # Rank of the LoRA matrices (higher = more capacity but more parameters)
  # Typical values: 8, 16, 32, 64. Start with 16-32 for IC-LoRA.
  rank: 32
  # Alpha scaling factor (usually set equal to rank)
  # The effective scaling is alpha/rank, so alpha=rank means scaling of 1.0
  alpha: 32
  # Dropout probability for LoRA layers (0.0 = no dropout)
  # Can help with regularization if overfitting occurs
  dropout: 0.0
  # Which transformer modules to apply LoRA to
  # The LTX-2 transformer has separate attention and FFN blocks for video and audio:
  #
  # VIDEO MODULES (not used for audio-only IC-LoRA):
  #   - attn1.to_k, attn1.to_q, attn1.to_v, attn1.to_out.0  (video self-attention)
  #   - attn2.to_k, attn2.to_q, attn2.to_v, attn2.to_out.0  (video cross-attention to text)
  #   - ff.net.0.proj, ff.net.2                             (video feed-forward)
  #
  # AUDIO MODULES:
  #   - audio_attn1.to_k, audio_attn1.to_q, audio_attn1.to_v, audio_attn1.to_out.0  (audio self-attention)
  #   - audio_attn2.to_k, audio_attn2.to_q, audio_attn2.to_v, audio_attn2.to_out.0  (audio cross-attention to text)
  #   - audio_ff.net.0.proj, audio_ff.net.2                                         (audio feed-forward)
  #
  # AUDIO-VIDEO CROSS-ATTENTION MODULES (not used for audio-only IC-LoRA):
  #   - audio_to_video_attn.to_k, audio_to_video_attn.to_q, audio_to_video_attn.to_v, audio_to_video_attn.to_out.0
  #       (Q from video, K/V from audio - allows video to attend to audio features)
  #   - video_to_audio_attn.to_k, video_to_audio_attn.to_q, video_to_audio_attn.to_v, video_to_audio_attn.to_out.0
  #       (Q from audio, K/V from video - allows audio to attend to video features)
  #
  # For audio-only IC-LoRA, we explicitly target audio modules.
  # Including audio FFN layers often improves transformation quality.
  target_modules:
    # Audio self-attention
    - "audio_attn1.to_k"
    - "audio_attn1.to_q"
    - "audio_attn1.to_v"
    - "audio_attn1.to_out.0"
    # Audio cross-attention to text
    - "audio_attn2.to_k"
    - "audio_attn2.to_q"
    - "audio_attn2.to_v"
    - "audio_attn2.to_out.0"
    # Audio feed-forward (often improves transformation quality)
    - "audio_ff.net.0.proj"
    - "audio_ff.net.2"
 # -----------------------------------------------------------------------------
 # Training Strategy Configuration
 # -----------------------------------------------------------------------------
 # Defines the audio-to-audio (IC-LoRA) training approach using the unified
 # flexible strategy. Reference conditioning concatenates pre-encoded reference
 # audio latents to the target sequence. Reference tokens participate in
 # bidirectional self-attention but receive no noise and are excluded from loss.
 training_strategy:
  # Strategy name: "flexible" for the unified conditioning framework
  # Supports all training modes (T2V, I2V, V2V, A2V, V2A, etc.) through
  # modality-specific configuration blocks.
  name: "flexible"
  # Audio modality configuration (audio-only, no video)
  audio:
    # Whether the model generates audio (true) or uses it as frozen conditioning (false)
    is_generated: true
    # Directory name (within preprocessed_data_root) containing target audio latents
    latents_dir: "audio_latents"
    # Conditions applied to the audio modality during training
    conditions:
      # Reference conditioning (IC-LoRA): concatenates pre-encoded reference audio
      # latents to the target sequence. The model learns to transform the reference
      # into the target audio based on the text prompt.
      - type: reference
        # Directory name (within preprocessed_data_root) containing reference audio latents
        # These are the conditioning inputs that guide the transformation
        latents_dir: "reference_audio_latents"
        # Probability of applying reference conditioning per training sample
        probability: 1.0
 # -----------------------------------------------------------------------------
 # Optimization Configuration
 # -----------------------------------------------------------------------------
 # Controls the training optimization parameters.
 optimization:
  # Learning rate for the optimizer
  # Typical range for LoRA: 1e-5 to 1e-4
  learning_rate: 2e-4
  # Total number of training steps
  steps: 3000
  # Batch size per GPU
  # Reduce if running out of memory
  batch_size: 1
  # Number of gradient accumulation steps
  # Effective batch size = batch_size * gradient_accumulation_steps * num_gpus
  gradient_accumulation_steps: 1
  # Maximum gradient norm for clipping (helps training stability)
  max_grad_norm: 1.0
  # Optimizer type: "adamw" (standard) or "adamw8bit" (memory-efficient)
  optimizer_type: "adamw"
  # Learning rate scheduler type
  # Options: "constant", "linear", "cosine", "cosine_with_restarts", "polynomial"
  scheduler_type: "linear"
  # Additional scheduler parameters (depends on scheduler_type)
  scheduler_params: { }
  # Enable gradient checkpointing to reduce memory usage
  # Recommended for training with limited GPU memory
  enable_gradient_checkpointing: true
 # -----------------------------------------------------------------------------
 # Acceleration Configuration
 # -----------------------------------------------------------------------------
 # Hardware acceleration and memory optimization settings.
 acceleration:
  # Mixed precision training mode
  # Options: "no" (fp32), "fp16" (half precision), "bf16" (bfloat16, recommended)
  mixed_precision_mode: "bf16"
  # Model quantization for reduced memory usage
  # Options: null (none), "int8-quanto", "int4-quanto", "int2-quanto", "fp8-quanto", "fp8uz-quanto"
  quantization: null
  # Load text encoder in 8-bit precision to save memory
  # Useful when GPU memory is limited
  load_text_encoder_in_8bit: false
  # Offload optimizer state to CPU during validation video sampling and restore it after.
  # Frees VRAM for the VAE decoder when optimizer state is large (full fine-tune, high-rank
  # LoRA). No effect under FSDP (sharded state).
  offload_optimizer_during_validation: false
 # -----------------------------------------------------------------------------
 # Data Configuration
 # -----------------------------------------------------------------------------
 # Specifies the training data location and loading parameters.
 data:
  # Root directory containing preprocessed training data
  # Should contain: audio_latents/, conditions/, and reference_audio_latents/ subdirectories
  preprocessed_data_root: "/path/to/preprocessed/data"
  # Number of worker processes for data loading
  # Used for parallel data loading to speed up data loading
  num_dataloader_workers: 2
 # -----------------------------------------------------------------------------
 # Validation Configuration
 # -----------------------------------------------------------------------------
 # Controls validation sampling during training.
 # NOTE: Validation sampling use simplified inference pipelines and prioritizes speed over
 # maximum quality. For production-quality inference, use `packages/ltx-pipelines`.
 validation:
  # Validation samples — each sample describes a self-contained generation request.
  # For IC-LoRA, each sample includes a reference condition pointing to the conditioning audio.
  samples:
    - prompt: >-
        A warm and soothing piano melody with soft ambient textures, reminiscent of a quiet
        evening by the fireplace. Gentle reverb creates a sense of intimate space.
      conditions:
        - type: reference
          audio: "/path/to/reference_audio_1.wav"
    - prompt: >-
        Energetic electronic beats with pulsing synthesizer leads and crisp hi-hat patterns.
        Deep bass tones provide a driving rhythm underneath bright melodic arpeggios.
      conditions:
        - type: reference
          audio: "/path/to/reference_audio_2.wav"
  # Negative prompt to avoid unwanted artifacts
  negative_prompt: "worst quality, inconsistent motion, blurry, jittery, distorted"
  # Generation length control [width, height, frames]
  # With generate_video=false, width/height are unused; frames and frame_rate set audio duration.
  # Frames must satisfy: frames % 8 == 1 (e.g., 1, 9, 17, 25, 33, 41, 49, 57, 65, 73, 81, 89, ...)
  video_dims: [ 512, 512, 81 ]
  # Frame rate for generated videos
  frame_rate: 25.0
  # Random seed for reproducible validation outputs
  seed: 42
  # Number of denoising steps for validation inference
  # Higher values = better quality but slower generation
  inference_steps: 30
  # Generate validation videos every N training steps
  # Set to null to disable validation during training
  interval: 100
  # Classifier-free guidance scale
  # Higher values = stronger adherence to prompt but may introduce artifacts
  guidance_scale: 4.0
  # STG (Spatio-Temporal Guidance) parameters for improved video quality
  # STG is combined with CFG for better temporal coherence
  stg_scale: 1.0  # Recommended: 1.0 (0.0 disables STG)
  stg_blocks: [29]  # Recommended: single block 29
  stg_mode: "stg_av"  # "stg_av" skips both audio and video self-attention (suited to audio validation)
  # Whether to generate audio in validation samples
  # Can be enabled even when not training the audio branch
  generate_audio: true
  # Whether to generate video in validation samples
  # Disabled for audio-only IC-LoRA since no video modality is configured
  generate_video: false
  # Skip validation at the beginning of training (step 0)
  skip_initial_validation: false
 # -----------------------------------------------------------------------------
 # Checkpoint Configuration
 # -----------------------------------------------------------------------------
 # Controls model checkpoint saving during training.
 checkpoints:
  # Save a checkpoint every N steps
  # Set to null to disable intermediate checkpoints
  interval: 250
  # Number of most recent checkpoints to keep
  # Set to -1 to keep all checkpoints
  keep_last_n: 3
  # Precision to use when saving checkpoint weights
  # Options: "bfloat16" (default, smaller files) or "float32" (full precision)
  precision: "bfloat16"
 # -----------------------------------------------------------------------------
 # Flow Matching Configuration
 # -----------------------------------------------------------------------------
 # Parameters for the flow matching training objective.
 flow_matching:
  # Timestep sampling mode
  # "shifted_logit_normal" is recommended for LTX-2 models
  timestep_sampling_mode: "shifted_logit_normal"
  # Additional parameters for timestep sampling
  timestep_sampling_params: { }
 # -----------------------------------------------------------------------------
 # Hugging Face Hub Configuration
 # -----------------------------------------------------------------------------
 # Settings for uploading trained models to the Hugging Face Hub.
 hub:
  # Whether to push the trained model to the Hub
  push_to_hub: false
  # Repository ID on Hugging Face Hub (e.g., "username/my-ic-lora-model")
  # Required if push_to_hub is true
  hub_model_id: null
 # -----------------------------------------------------------------------------
 # Weights & Biases Configuration
 # -----------------------------------------------------------------------------
 # Settings for experiment tracking with W&B.
 wandb:
  # Enable W&B logging
  enabled: false
  # W&B project name
  project: "ltx-2-trainer"
  # W&B username or team (null uses default account)
  entity: null
  # Tags to help organize runs
  tags: [ "ltx2", "ic-lora", "a2a" ]
  # Log validation media (video/audio) to W&B
  log_validation_videos: true
 # -----------------------------------------------------------------------------
 # General Configuration
 # -----------------------------------------------------------------------------
 # Global settings for the training run.
 # Random seed for reproducibility
 seed: 42
 # Directory to save outputs (checkpoints, validation videos, logs)
 output_dir: "outputs/a2a_ic_lora"
@@ -1,344 +0,0 @@
 # =============================================================================
 # LTX-2 Audio-to-Video LoRA Training Configuration
 # =============================================================================
 #
 # This configuration is for training LoRA adapters on the LTX-2 model for
 # audio-to-video generation. The model learns to generate videos conditioned
 # on a frozen audio signal via the transformer's built-in cross-modal attention.
 #
 # In this mode, audio is provided as a frozen (clean, no noise, no loss)
 # conditioning signal. The video modality is the only generated output.
 # Audio influences video generation through the transformer's audio-to-video
 # cross-attention mechanism.
 #
 # Use this configuration when you want to:
 #   - Generate videos driven by audio content (e.g., music visualizations)
 #   - Train audio-reactive video generation
 #   - Create models that synchronize video with given audio
 #
 # Dataset structure:
 #   preprocessed_data_root/
 #   ├── latents/        # Video latents (VAE-encoded videos)
 #   ├── conditions/     # Text embeddings for each video
 #   └── audio_latents/  # Audio latents (frozen conditioning input)
 #
 # =============================================================================
 # -----------------------------------------------------------------------------
 # Model Configuration
 # -----------------------------------------------------------------------------
 # Specifies the base model to fine-tune and the training mode.
 model:
  # Path to the LTX-2 model checkpoint (.safetensors file)
  # This should be a local path to your downloaded model
  model_path: "path/to/ltx-2-model.safetensors"
  # Path to the text encoder model directory
  # For LTX-2, this is typically the Gemma-based text encoder
  text_encoder_path: "path/to/gemma-text-encoder"
  # Training mode: "lora" for efficient adapter training, "full" for full fine-tuning
  # LoRA is recommended for most use cases (faster, less memory, prevents overfitting)
  training_mode: "lora"
  # Optional: Path to resume training from a checkpoint
  # Can be a checkpoint file (.safetensors) or directory (uses latest checkpoint)
  load_checkpoint: null
 # -----------------------------------------------------------------------------
 # LoRA Configuration
 # -----------------------------------------------------------------------------
 # Controls the Low-Rank Adaptation parameters for efficient fine-tuning.
 lora:
  # Rank of the LoRA matrices (higher = more capacity but more parameters)
  # Typical values: 8, 16, 32, 64. Start with 32 for general fine-tuning.
  rank: 32
  # Alpha scaling factor (usually set equal to rank)
  # The effective scaling is alpha/rank, so alpha=rank means scaling of 1.0
  alpha: 32
  # Dropout probability for LoRA layers (0.0 = no dropout)
  # Can help with regularization if overfitting occurs
  dropout: 0.0
  # Which transformer modules to apply LoRA to
  # The LTX-2 transformer has separate attention and FFN blocks for video and audio:
  #
  # VIDEO MODULES:
  #   - attn1.to_k, attn1.to_q, attn1.to_v, attn1.to_out.0  (video self-attention)
  #   - attn2.to_k, attn2.to_q, attn2.to_v, attn2.to_out.0  (video cross-attention to text)
  #   - ff.net.0.proj, ff.net.2                             (video feed-forward)
  #
  # AUDIO MODULES:
  #   - audio_attn1.to_k, audio_attn1.to_q, audio_attn1.to_v, audio_attn1.to_out.0  (audio self-attention)
  #   - audio_attn2.to_k, audio_attn2.to_q, audio_attn2.to_v, audio_attn2.to_out.0  (audio cross-attention to text)
  #   - audio_ff.net.0.proj, audio_ff.net.2                                         (audio feed-forward)
  #
  # AUDIO-VIDEO CROSS-ATTENTION MODULES (for cross-modal interaction):
  #   - audio_to_video_attn.to_k, audio_to_video_attn.to_q, audio_to_video_attn.to_v, audio_to_video_attn.to_out.0
  #       (Q from video, K/V from audio - allows video to attend to audio features)
  #   - video_to_audio_attn.to_k, video_to_audio_attn.to_q, video_to_audio_attn.to_v, video_to_audio_attn.to_out.0
  #       (Q from audio, K/V from video - allows audio to attend to video features)
  #
  # Using short patterns like "to_k" matches ALL attention modules (video, audio, and cross-modal).
  # For audio-video training, this is the recommended approach.
  target_modules:
    # Attention layers (matches both video and audio branches)
    - "to_k"
    - "to_q"
    - "to_v"
    - "to_out.0"
    # Uncomment below to also train feed-forward layers (can increase the LoRA's capacity):
    # - "ff.net.0.proj"
    # - "ff.net.2"
    # - "audio_ff.net.0.proj"
    # - "audio_ff.net.2"
 # -----------------------------------------------------------------------------
 # Training Strategy Configuration
 # -----------------------------------------------------------------------------
 # Defines the audio-to-video training approach using the unified flexible strategy.
 # Audio is frozen (no noise, sigma=0, excluded from loss) and conditions video
 # generation via the transformer's built-in cross-modal attention.
 training_strategy:
  # Strategy name: "flexible" for the unified conditioning framework
  # Supports all training modes (T2V, I2V, V2V, A2V, V2A, etc.) through
  # modality-specific configuration blocks.
  name: "flexible"
  # Video modality configuration
  # Video is the generated (denoised) output
  video:
    # Whether the model generates video (true) or uses it as frozen conditioning (false)
    is_generated: true
    # Directory name (within preprocessed_data_root) containing video latents
    latents_dir: "latents"
  # Audio modality configuration
  # Audio is frozen — it acts as conditioning for video generation
  # Frozen modalities get sigma=0, timestep=0, no noise, and no loss
  audio:
    # Whether the model generates audio (true) or uses it as frozen conditioning (false)
    # When false, audio is passed through the transformer clean and influences
    # video via cross-modal attention
    is_generated: false
    # Directory name (within preprocessed_data_root) containing audio latents
    latents_dir: "audio_latents"
 # -----------------------------------------------------------------------------
 # Optimization Configuration
 # -----------------------------------------------------------------------------
 # Controls the training optimization parameters.
 optimization:
  # Learning rate for the optimizer
  # Typical range for LoRA: 1e-5 to 1e-4
  learning_rate: 1e-4
  # Total number of training steps
  steps: 2000
  # Batch size per GPU
  # Reduce if running out of memory
  batch_size: 1
  # Number of gradient accumulation steps
  # Effective batch size = batch_size * gradient_accumulation_steps * num_gpus
  gradient_accumulation_steps: 1
  # Maximum gradient norm for clipping (helps training stability)
  max_grad_norm: 1.0
  # Optimizer type: "adamw" (standard) or "adamw8bit" (memory-efficient)
  optimizer_type: "adamw"
  # Learning rate scheduler type
  # Options: "constant", "linear", "cosine", "cosine_with_restarts", "polynomial"
  scheduler_type: "linear"
  # Additional scheduler parameters (depends on scheduler_type)
  scheduler_params: { }
  # Enable gradient checkpointing to reduce memory usage
  # Recommended for training with limited GPU memory
  enable_gradient_checkpointing: true
 # -----------------------------------------------------------------------------
 # Acceleration Configuration
 # -----------------------------------------------------------------------------
 # Hardware acceleration and memory optimization settings.
 acceleration:
  # Mixed precision training mode
  # Options: "no" (fp32), "fp16" (half precision), "bf16" (bfloat16, recommended)
  mixed_precision_mode: "bf16"
  # Model quantization for reduced memory usage
  # Options: null (none), "int8-quanto", "int4-quanto", "int2-quanto", "fp8-quanto", "fp8uz-quanto"
  quantization: null
  # Load text encoder in 8-bit precision to save memory
  # Useful when GPU memory is limited
  load_text_encoder_in_8bit: false
  # Offload optimizer state to CPU during validation video sampling and restore it after.
  # Frees VRAM for the VAE decoder when optimizer state is large (full fine-tune, high-rank
  # LoRA). No effect under FSDP (sharded state).
  offload_optimizer_during_validation: false
 # -----------------------------------------------------------------------------
 # Data Configuration
 # -----------------------------------------------------------------------------
 # Specifies the training data location and loading parameters.
 data:
  # Root directory containing preprocessed training data
  # Should contain: latents/, audio_latents/, and conditions/
  preprocessed_data_root: "/path/to/preprocessed/data"
  # Number of worker processes for data loading
  # Used for parallel data loading to speed up data loading
  num_dataloader_workers: 2
 # -----------------------------------------------------------------------------
 # Validation Configuration
 # -----------------------------------------------------------------------------
 # Controls validation sampling during training.
 # NOTE: Validation sampling use simplified inference pipelines and prioritizes speed over
 # maximum quality. For production-quality inference, use `packages/ltx-pipelines`.
 validation:
  # Validation samples — each sample describes a self-contained generation request.
  # Use 'conditions' to add conditioning (first_frame, prefix, suffix, reference, video_to_audio, etc.)
  # See docs/configuration-reference.md#validation-condition-types for the full list of condition types.
  samples:
    - prompt: >-
        A musician plays an acoustic guitar in a dimly lit recording studio, fingers moving
        across the fretboard with practiced ease. The warm amber light from a desk lamp
        illuminates the wooden guitar body. Sound-absorbing panels line the walls, and a
        microphone stands nearby on a boom arm.
      conditions:
        - type: audio_to_video
          audio: "/path/to/conditioning_audio_1.wav"
    - prompt: >-
        Rain falls steadily on a cobblestone street in a European town at dusk. Puddles form
        between the stones, creating ripples as new drops land. Old brick buildings line both
        sides of the narrow street, their facades glistening with moisture under warm
        streetlights.
      conditions:
        - type: audio_to_video
          audio: "/path/to/conditioning_audio_2.wav"
  # Negative prompt to avoid unwanted artifacts
  negative_prompt: "worst quality, inconsistent motion, blurry, jittery, distorted"
  # Output video dimensions [width, height, frames]
  # Width and height must be divisible by 32
  # Frames must satisfy: frames % 8 == 1 (e.g., 1, 9, 17, 25, 33, 41, 49, 57, 65, 73, 81, 89, ...)
  video_dims: [ 576, 576, 89 ]
  # Frame rate for generated videos
  frame_rate: 25.0
  # Random seed for reproducible validation outputs
  seed: 42
  # Number of denoising steps for validation inference
  # Higher values = better quality but slower generation
  inference_steps: 30
  # Generate validation videos every N training steps
  # Set to null to disable validation during training
  interval: 100
  # Classifier-free guidance scale
  # Higher values = stronger adherence to prompt but may introduce artifacts
  guidance_scale: 4.0
  # STG (Spatio-Temporal Guidance) parameters for improved video quality
  # STG is combined with CFG for better temporal coherence
  stg_scale: 1.0  # Recommended: 1.0 (0.0 disables STG)
  stg_blocks: [29]  # Recommended: single block 29
  stg_mode: "stg_v"  # "stg_av" perturbs both audio and video, "stg_v" video only
  # Whether to generate audio in validation samples
  # Independent of training_strategy.audio.is_generated - you can generate audio
  # in validation even when not training the audio branch
  # For this audio-to-video config, false matches frozen audio conditioning (video-only synthesis).
  generate_audio: false
  # Generate video from the frozen audio condition
  generate_video: true
  # Skip validation at the beginning of training (step 0)
  skip_initial_validation: false
 # -----------------------------------------------------------------------------
 # Checkpoint Configuration
 # -----------------------------------------------------------------------------
 # Controls model checkpoint saving during training.
 checkpoints:
  # Save a checkpoint every N steps
  # Set to null to disable intermediate checkpoints
  interval: 250
  # Number of most recent checkpoints to keep
  # Set to -1 to keep all checkpoints
  keep_last_n: -1
  # Precision to use when saving checkpoint weights
  # Options: "bfloat16" (default, smaller files) or "float32" (full precision)
  precision: "bfloat16"
 # -----------------------------------------------------------------------------
 # Flow Matching Configuration
 # -----------------------------------------------------------------------------
 # Parameters for the flow matching training objective.
 flow_matching:
  # Timestep sampling mode
  # "shifted_logit_normal" is recommended for LTX-2 models
  timestep_sampling_mode: "shifted_logit_normal"
  # Additional parameters for timestep sampling
  timestep_sampling_params: { }
 # -----------------------------------------------------------------------------
 # Hugging Face Hub Configuration
 # -----------------------------------------------------------------------------
 # Settings for uploading trained models to the Hugging Face Hub.
 hub:
  # Whether to push the trained model to the Hub
  push_to_hub: false
  # Repository ID on Hugging Face Hub (e.g., "username/my-lora-model")
  # Required if push_to_hub is true
  hub_model_id: null
 # -----------------------------------------------------------------------------
 # Weights & Biases Configuration
 # -----------------------------------------------------------------------------
 # Settings for experiment tracking with W&B.
 wandb:
  # Enable W&B logging
  enabled: false
  # W&B project name
  project: "ltx-2-trainer"
  # W&B username or team (null uses default account)
  entity: null
  # Tags to help organize runs
  tags: [ "ltx2", "lora", "a2v" ]
  # Log validation media (video/audio) to W&B
  log_validation_videos: true
 # -----------------------------------------------------------------------------
 # General Configuration
 # -----------------------------------------------------------------------------
 # Global settings for the training run.
 # Random seed for reproducibility
 seed: 42
 # Directory to save outputs (checkpoints, validation videos, logs)
 output_dir: "outputs/a2v_lora"
@@ -1,343 +0,0 @@
 # =============================================================================
 # LTX-2 Audio Extension (Forward) LoRA Training Configuration
 # =============================================================================
 #
 # This configuration is for training LoRA adapters on the LTX-2 model for
 # forward audio extension. The model learns to continue audio forward in time
 # by conditioning on a prefix of existing audio latent timesteps.
 #
 # Prefix conditioning works by providing the first N audio latent timesteps as
 # clean conditioning signals during training — they receive no noise,
 # timestep=0, and are excluded from the loss. The model learns to generate
 # audio that seamlessly continues from the given prefix.
 #
 # This is an audio-only training mode — no video modality is configured.
 #
 # Use this configuration when you want to:
 #   - Train the model to extend/continue existing audio
 #   - Fine-tune audio temporal continuation capabilities
 #   - Create seamless audio extension models
 #
 # Dataset structure:
 #   preprocessed_data_root/
 #   ├── conditions/      # Text embeddings for each sample
 #   └── audio_latents/   # Audio latents (VAE-encoded audio)
 #
 # =============================================================================
 # -----------------------------------------------------------------------------
 # Model Configuration
 # -----------------------------------------------------------------------------
 # Specifies the base model to fine-tune and the training mode.
 model:
  # Path to the LTX-2 model checkpoint (.safetensors file)
  # This should be a local path to your downloaded model
  model_path: "path/to/ltx-2-model.safetensors"
  # Path to the text encoder model directory
  # For LTX-2, this is typically the Gemma-based text encoder
  text_encoder_path: "path/to/gemma-text-encoder"
  # Training mode: "lora" for efficient adapter training, "full" for full fine-tuning
  # LoRA is recommended for most use cases (faster, less memory, prevents overfitting)
  training_mode: "lora"
  # Optional: Path to resume training from a checkpoint
  # Can be a checkpoint file (.safetensors) or directory (uses latest checkpoint)
  load_checkpoint: null
 # -----------------------------------------------------------------------------
 # LoRA Configuration
 # -----------------------------------------------------------------------------
 # Controls the Low-Rank Adaptation parameters for efficient fine-tuning.
 lora:
  # Rank of the LoRA matrices (higher = more capacity but more parameters)
  # Typical values: 8, 16, 32, 64. Start with 32 for audio extension LoRA training.
  rank: 32
  # Alpha scaling factor (usually set equal to rank)
  # The effective scaling is alpha/rank, so alpha=rank means scaling of 1.0
  alpha: 32
  # Dropout probability for LoRA layers (0.0 = no dropout)
  # Can help with regularization if overfitting occurs
  dropout: 0.0
  # Which transformer modules to apply LoRA to
  # The LTX-2 transformer has separate attention and FFN blocks for video and audio:
  #
  # VIDEO MODULES (not used for audio-only modes):
  #   - attn1.to_k, attn1.to_q, attn1.to_v, attn1.to_out.0  (video self-attention)
  #   - attn2.to_k, attn2.to_q, attn2.to_v, attn2.to_out.0  (video cross-attention to text)
  #   - ff.net.0.proj, ff.net.2                             (video feed-forward)
  #
  # AUDIO MODULES:
  #   - audio_attn1.to_k, audio_attn1.to_q, audio_attn1.to_v, audio_attn1.to_out.0  (audio self-attention)
  #   - audio_attn2.to_k, audio_attn2.to_q, audio_attn2.to_v, audio_attn2.to_out.0  (audio cross-attention to text)
  #   - audio_ff.net.0.proj, audio_ff.net.2                                         (audio feed-forward)
  #
  # AUDIO-VIDEO CROSS-ATTENTION MODULES (not used for audio-only modes):
  #   - audio_to_video_attn.to_k, audio_to_video_attn.to_q, audio_to_video_attn.to_v, audio_to_video_attn.to_out.0
  #       (Q from video, K/V from audio - allows video to attend to audio features)
  #   - video_to_audio_attn.to_k, video_to_audio_attn.to_q, video_to_audio_attn.to_v, video_to_audio_attn.to_out.0
  #       (Q from audio, K/V from video - allows audio to attend to video features)
  #
  # For audio-only extension, we explicitly target audio modules.
  # Including audio FFN layers can increase the LoRA's capacity.
  target_modules:
    # Audio self-attention
    - "audio_attn1.to_k"
    - "audio_attn1.to_q"
    - "audio_attn1.to_v"
    - "audio_attn1.to_out.0"
    # Audio cross-attention to text
    - "audio_attn2.to_k"
    - "audio_attn2.to_q"
    - "audio_attn2.to_v"
    - "audio_attn2.to_out.0"
    # Audio feed-forward (often improves transformation quality)
    - "audio_ff.net.0.proj"
    - "audio_ff.net.2"
 # -----------------------------------------------------------------------------
 # Training Strategy Configuration
 # -----------------------------------------------------------------------------
 # Defines the audio extension training approach using the unified flexible
 # strategy. Prefix conditioning provides the first N audio latent timesteps as
 # clean conditioning, teaching the model to generate temporal continuations.
 training_strategy:
  name: "flexible"
  # Audio modality configuration (audio-only, no video)
  audio:
    # Whether the model generates audio (true) or uses it as frozen conditioning (false)
    is_generated: true
    # Directory name (within preprocessed_data_root) containing audio latents
    latents_dir: "audio_latents"
    # Conditions applied to the audio modality during training
    conditions:
      - type: prefix
        # Number of audio latent timesteps to use as conditioning prefix
        # Each audio latent timestep = 1 patchified token
        temporal_boundary: 8
        # Probability of applying prefix conditioning per training sample
        # At 1.0, all training samples use audio extension mode
        probability: 1.0
 # -----------------------------------------------------------------------------
 # Optimization Configuration
 # -----------------------------------------------------------------------------
 # Controls the training optimization parameters.
 optimization:
  # Learning rate for the optimizer
  # Typical range for LoRA: 1e-5 to 1e-4
  learning_rate: 2e-4
  # Total number of training steps
  steps: 3000
  # Batch size per GPU
  # Reduce if running out of memory
  batch_size: 1
  # Number of gradient accumulation steps
  # Effective batch size = batch_size * gradient_accumulation_steps * num_gpus
  gradient_accumulation_steps: 1
  # Maximum gradient norm for clipping (helps training stability)
  max_grad_norm: 1.0
  # Optimizer type: "adamw" (standard) or "adamw8bit" (memory-efficient)
  optimizer_type: "adamw"
  # Learning rate scheduler type
  # Options: "constant", "linear", "cosine", "cosine_with_restarts", "polynomial"
  scheduler_type: "linear"
  # Additional scheduler parameters (depends on scheduler_type)
  scheduler_params: { }
  # Enable gradient checkpointing to reduce memory usage
  # Recommended for training with limited GPU memory
  enable_gradient_checkpointing: true
 # -----------------------------------------------------------------------------
 # Acceleration Configuration
 # -----------------------------------------------------------------------------
 # Hardware acceleration and memory optimization settings.
 acceleration:
  # Mixed precision training mode
  # Options: "no" (fp32), "fp16" (half precision), "bf16" (bfloat16, recommended)
  mixed_precision_mode: "bf16"
  # Model quantization for reduced memory usage
  # Options: null (none), "int8-quanto", "int4-quanto", "int2-quanto", "fp8-quanto", "fp8uz-quanto"
  quantization: null
  # Load text encoder in 8-bit precision to save memory
  # Useful when GPU memory is limited
  load_text_encoder_in_8bit: false
  # Offload optimizer state to CPU during validation video sampling and restore it after.
  # Frees VRAM for the VAE decoder when optimizer state is large (full fine-tune, high-rank
  # LoRA). No effect under FSDP (sharded state).
  offload_optimizer_during_validation: false
 # -----------------------------------------------------------------------------
 # Data Configuration
 # -----------------------------------------------------------------------------
 # Specifies the training data location and loading parameters.
 data:
  # Root directory containing preprocessed training data
  # Should contain: conditions/ and audio_latents/ subdirectories
  preprocessed_data_root: "/path/to/preprocessed/data"
  # Number of worker processes for data loading
  # Used for parallel data loading to speed up data loading
  num_dataloader_workers: 2
 # -----------------------------------------------------------------------------
 # Validation Configuration
 # -----------------------------------------------------------------------------
 # Controls validation sampling during training.
 # NOTE: Validation sampling use simplified inference pipelines and prioritizes speed over
 # maximum quality. For production-quality inference, use `packages/ltx-pipelines`.
 validation:
  # Validation samples — each sample describes a self-contained generation request.
  # Each sample includes an audio prefix condition for forward audio extension.
  samples:
    - prompt: >-
        A warm and soothing piano melody with soft ambient textures, reminiscent of a quiet
        evening by the fireplace. Gentle reverb creates a sense of intimate space.
      conditions:
        - type: prefix
          audio: "/path/to/prefix_audio_1.wav"
          # Duration is in seconds; choose a value that covers a comparable audio context
          # to the training temporal_boundary measured in audio latent timesteps.
          duration: 1.0
    - prompt: >-
        Energetic electronic beats with pulsing synthesizer leads and crisp hi-hat patterns.
        Deep bass tones provide a driving rhythm underneath bright melodic arpeggios.
      conditions:
        - type: prefix
          audio: "/path/to/prefix_audio_2.wav"
          # Duration is in seconds; choose a value that covers a comparable audio context
          # to the training temporal_boundary measured in audio latent timesteps.
          duration: 1.0
  # Negative prompt to avoid unwanted artifacts
  negative_prompt: "worst quality, inconsistent motion, blurry, jittery, distorted"
  # Generation length control [width, height, frames]
  # With generate_video=false, width/height are unused; frames and frame_rate set audio duration.
  # Frames must satisfy: frames % 8 == 1 (e.g., 1, 9, 17, 25, 33, 41, 49, 57, 65, 73, 81, 89, ...)
  video_dims: [ 512, 512, 81 ]
  # Frame rate for generated videos
  frame_rate: 25.0
  # Random seed for reproducible validation outputs
  seed: 42
  # Number of denoising steps for validation inference
  # Higher values = better quality but slower generation
  inference_steps: 30
  # Generate validation videos every N training steps
  # Set to null to disable validation during training
  interval: 100
  # Classifier-free guidance scale
  # Higher values = stronger adherence to prompt but may introduce artifacts
  guidance_scale: 4.0
  # STG (Spatio-Temporal Guidance) parameters for improved video quality
  # STG is combined with CFG for better temporal coherence
  stg_scale: 1.0  # Recommended: 1.0 (0.0 disables STG)
  stg_blocks: [29]  # Recommended: single block 29
  stg_mode: "stg_av"  # "stg_av" skips both audio and video self-attention (suited to audio validation)
  # Whether to generate audio in validation samples
  # Enabled because this audio-only config generates audio
  generate_audio: true
  # Whether to generate video in validation samples
  # Disabled because no video modality is configured
  generate_video: false
  # Skip validation at the beginning of training (step 0)
  skip_initial_validation: false
 # -----------------------------------------------------------------------------
 # Checkpoint Configuration
 # -----------------------------------------------------------------------------
 # Controls model checkpoint saving during training.
 checkpoints:
  # Save a checkpoint every N steps
  # Set to null to disable intermediate checkpoints
  interval: 250
  # Number of most recent checkpoints to keep
  # Set to -1 to keep all checkpoints
  keep_last_n: 3
  # Precision to use when saving checkpoint weights
  # Options: "bfloat16" (default, smaller files) or "float32" (full precision)
  precision: "bfloat16"
 # -----------------------------------------------------------------------------
 # Flow Matching Configuration
 # -----------------------------------------------------------------------------
 # Parameters for the flow matching training objective.
 flow_matching:
  # Timestep sampling mode
  # "shifted_logit_normal" is recommended for LTX-2 models
  timestep_sampling_mode: "shifted_logit_normal"
  # Additional parameters for timestep sampling
  timestep_sampling_params: { }
 # -----------------------------------------------------------------------------
 # Hugging Face Hub Configuration
 # -----------------------------------------------------------------------------
 # Settings for uploading trained models to the Hugging Face Hub.
 hub:
  # Whether to push the trained model to the Hub
  push_to_hub: false
  # Repository ID on Hugging Face Hub (e.g., "username/my-ic-lora-model")
  # Required if push_to_hub is true
  hub_model_id: null
 # -----------------------------------------------------------------------------
 # Weights & Biases Configuration
 # -----------------------------------------------------------------------------
 # Settings for experiment tracking with W&B.
 wandb:
  # Enable W&B logging
  enabled: false
  # W&B project name
  project: "ltx-2-trainer"
  # W&B username or team (null uses default account)
  entity: null
  # Tags to help organize runs
  tags: [ "ltx2", "lora", "audio-extension", "audio-only" ]
  # Log validation media (video/audio) to W&B
  log_validation_videos: true
 # -----------------------------------------------------------------------------
 # General Configuration
 # -----------------------------------------------------------------------------
 # Global settings for the training run.
 # Random seed for reproducibility
 seed: 42
 # Directory to save outputs (checkpoints, validation videos, logs)
 output_dir: "outputs/audio_extend_lora"
@@ -1,324 +0,0 @@
 # =============================================================================
 # LTX-2 Audio Inpainting LoRA Training Configuration
 # =============================================================================
 #
 # This configuration is for training LoRA adapters on the LTX-2 model for
 # audio inpainting. The model learns to fill in masked regions of audio
 # using per-sample binary masks that define which regions are conditioning
 # (provided clean) and which regions the model must generate.
 #
 # Mask conditioning works by loading per-sample binary masks from disk.
 # Masked regions receive clean latents (no noise, timestep=0) and are excluded
 # from the loss. Unmasked regions are noised and trained normally.
 #
 # This is an audio-only training mode — no video modality is configured.
 #
 # Use this configuration when you want to:
 #   - Train the model to fill in or replace regions of existing audio
 #   - Fine-tune audio inpainting capabilities on custom datasets
 #   - Create audio restoration or editing models
 #
 # Dataset structure:
 #   preprocessed_data_root/
 #   ├── conditions/      # Text embeddings for each sample
 #   ├── audio_latents/   # Audio latents (VAE-encoded audio)
 #   └── audio_masks/     # Per-sample binary masks defining conditioning regions
 #
 # Dataset metadata columns: audio, audio_mask, caption
 #
 # =============================================================================
 # -----------------------------------------------------------------------------
 # Model Configuration
 # -----------------------------------------------------------------------------
 # Specifies the base model to fine-tune and the training mode.
 model:
  # Path to the LTX-2 model checkpoint (.safetensors file)
  # This should be a local path to your downloaded model
  model_path: "path/to/ltx-2-model.safetensors"
  # Path to the text encoder model directory
  # For LTX-2, this is typically the Gemma-based text encoder
  text_encoder_path: "path/to/gemma-text-encoder"
  # Training mode: "lora" for efficient adapter training, "full" for full fine-tuning
  # LoRA is recommended for most use cases (faster, less memory, prevents overfitting)
  training_mode: "lora"
  # Optional: Path to resume training from a checkpoint
  # Can be a checkpoint file (.safetensors) or directory (uses latest checkpoint)
  load_checkpoint: null
 # -----------------------------------------------------------------------------
 # LoRA Configuration
 # -----------------------------------------------------------------------------
 # Controls the Low-Rank Adaptation parameters for efficient fine-tuning.
 lora:
  # Rank of the LoRA matrices (higher = more capacity but more parameters)
  # Typical values: 8, 16, 32, 64. Start with 32 for audio inpainting LoRA training.
  rank: 32
  # Alpha scaling factor (usually set equal to rank)
  # The effective scaling is alpha/rank, so alpha=rank means scaling of 1.0
  alpha: 32
  # Dropout probability for LoRA layers (0.0 = no dropout)
  # Can help with regularization if overfitting occurs
  dropout: 0.0
  # For audio-only inpainting, we explicitly target audio modules.
  # Including audio FFN layers can increase the LoRA's capacity.
  target_modules:
    # Audio self-attention
    - "audio_attn1.to_k"
    - "audio_attn1.to_q"
    - "audio_attn1.to_v"
    - "audio_attn1.to_out.0"
    # Audio cross-attention to text
    - "audio_attn2.to_k"
    - "audio_attn2.to_q"
    - "audio_attn2.to_v"
    - "audio_attn2.to_out.0"
    # Audio feed-forward (often improves transformation quality)
    - "audio_ff.net.0.proj"
    - "audio_ff.net.2"
 # -----------------------------------------------------------------------------
 # Training Strategy Configuration
 # -----------------------------------------------------------------------------
 # Defines the audio inpainting training approach using the unified flexible
 # strategy. Per-sample binary masks define which audio regions are provided
 # as clean conditioning and which regions the model must learn to generate.
 training_strategy:
  name: "flexible"
  # Audio modality configuration (audio-only, no video)
  audio:
    # Whether the model generates audio (true) or uses it as frozen conditioning (false)
    is_generated: true
    # Directory name (within preprocessed_data_root) containing audio latents
    latents_dir: "audio_latents"
    # Conditions applied to the audio modality during training
    conditions:
      - type: mask
        # Directory name (within preprocessed_data_root) containing binary masks
        # Each mask file corresponds to a training sample and defines the
        # conditioning region (mask=1 means conditioning, mask=0 means generate)
        mask_dir: "audio_masks"
        # Probability of applying mask conditioning per training sample
        # At 1.0, all training samples use inpainting mode
        probability: 1.0
 # -----------------------------------------------------------------------------
 # Optimization Configuration
 # -----------------------------------------------------------------------------
 # Controls the training optimization parameters.
 optimization:
  # Learning rate for the optimizer
  # Typical range for LoRA: 1e-5 to 1e-4
  learning_rate: 2e-4
  # Total number of training steps
  steps: 3000
  # Batch size per GPU
  # Reduce if running out of memory
  batch_size: 1
  # Number of gradient accumulation steps
  # Effective batch size = batch_size * gradient_accumulation_steps * num_gpus
  gradient_accumulation_steps: 1
  # Maximum gradient norm for clipping (helps training stability)
  max_grad_norm: 1.0
  # Optimizer type: "adamw" (standard) or "adamw8bit" (memory-efficient)
  optimizer_type: "adamw"
  # Learning rate scheduler type
  # Options: "constant", "linear", "cosine", "cosine_with_restarts", "polynomial"
  scheduler_type: "linear"
  # Additional scheduler parameters (depends on scheduler_type)
  scheduler_params: { }
  # Enable gradient checkpointing to reduce memory usage
  # Recommended for training with limited GPU memory
  enable_gradient_checkpointing: true
 # -----------------------------------------------------------------------------
 # Acceleration Configuration
 # -----------------------------------------------------------------------------
 # Hardware acceleration and memory optimization settings.
 acceleration:
  # Mixed precision training mode
  # Options: "no" (fp32), "fp16" (half precision), "bf16" (bfloat16, recommended)
  mixed_precision_mode: "bf16"
  # Model quantization for reduced memory usage
  # Options: null (none), "int8-quanto", "int4-quanto", "int2-quanto", "fp8-quanto", "fp8uz-quanto"
  quantization: null
  # Load text encoder in 8-bit precision to save memory
  # Useful when GPU memory is limited
  load_text_encoder_in_8bit: false
  # Offload optimizer state to CPU during validation video sampling and restore it after.
  # Frees VRAM for the VAE decoder when optimizer state is large (full fine-tune, high-rank
  # LoRA). No effect under FSDP (sharded state).
  offload_optimizer_during_validation: false
 # -----------------------------------------------------------------------------
 # Data Configuration
 # -----------------------------------------------------------------------------
 # Specifies the training data location and loading parameters.
 data:
  # Root directory containing preprocessed training data
  # Should contain: conditions/, audio_latents/, and audio_masks/ subdirectories
  preprocessed_data_root: "/path/to/preprocessed/data"
  # Number of worker processes for data loading
  # Used for parallel data loading to speed up data loading
  num_dataloader_workers: 2
 # -----------------------------------------------------------------------------
 # Validation Configuration
 # -----------------------------------------------------------------------------
 # Controls validation sampling during training.
 # NOTE: Validation sampling use simplified inference pipelines and prioritizes speed over
 # maximum quality. For production-quality inference, use `packages/ltx-pipelines`.
 validation:
  # Validation samples — each sample describes a self-contained generation request.
  # For audio inpainting, each sample includes mask conditioning (audio + mask paths).
  samples:
    - prompt: >-
        A warm and soothing piano melody with soft ambient textures, reminiscent of a quiet
        evening by the fireplace. Gentle reverb creates a sense of intimate space.
      conditions:
        - type: mask
          audio: "/path/to/inpainting_audio_1.wav"
          mask: "/path/to/inpainting_mask_1.pt"
    - prompt: >-
        Energetic electronic beats with pulsing synthesizer leads and crisp hi-hat patterns.
        Deep bass tones provide a driving rhythm underneath bright melodic arpeggios.
      conditions:
        - type: mask
          audio: "/path/to/inpainting_audio_2.wav"
          mask: "/path/to/inpainting_mask_2.pt"
  # Negative prompt to avoid unwanted artifacts
  negative_prompt: "worst quality, inconsistent motion, blurry, jittery, distorted"
  # Generation length control [width, height, frames]
  # With generate_video=false, width/height are unused; frames and frame_rate set audio duration.
  # Frames must satisfy: frames % 8 == 1 (e.g., 1, 9, 17, 25, 33, 41, 49, 57, 65, 73, 81, 89, ...)
  video_dims: [ 512, 512, 81 ]
  # Frame rate for generated videos
  frame_rate: 25.0
  # Random seed for reproducible validation outputs
  seed: 42
  # Number of denoising steps for validation inference
  # Higher values = better quality but slower generation
  inference_steps: 30
  # Generate validation videos every N training steps
  # Set to null to disable validation during training
  interval: 100
  # Classifier-free guidance scale
  # Higher values = stronger adherence to prompt but may introduce artifacts
  guidance_scale: 4.0
  # STG (Spatio-Temporal Guidance) parameters for improved video quality
  # STG is combined with CFG for better temporal coherence
  stg_scale: 1.0  # Recommended: 1.0 (0.0 disables STG)
  stg_blocks: [29]  # Recommended: single block 29
  stg_mode: "stg_av"  # "stg_av" skips both audio and video self-attention (suited to audio validation)
  # Whether to generate audio in validation samples
  # Enabled because this audio-only config generates audio
  generate_audio: true
  # Whether to generate video in validation samples
  # Disabled because no video modality is configured
  generate_video: false
  # Skip validation at the beginning of training (step 0)
  skip_initial_validation: false
 # -----------------------------------------------------------------------------
 # Checkpoint Configuration
 # -----------------------------------------------------------------------------
 # Controls model checkpoint saving during training.
 checkpoints:
  # Save a checkpoint every N steps
  # Set to null to disable intermediate checkpoints
  interval: 250
  # Number of most recent checkpoints to keep
  # Set to -1 to keep all checkpoints
  keep_last_n: 3
  # Precision to use when saving checkpoint weights
  # Options: "bfloat16" (default, smaller files) or "float32" (full precision)
  precision: "bfloat16"
 # -----------------------------------------------------------------------------
 # Flow Matching Configuration
 # -----------------------------------------------------------------------------
 # Parameters for the flow matching training objective.
 flow_matching:
  # Timestep sampling mode
  # "shifted_logit_normal" is recommended for LTX-2 models
  timestep_sampling_mode: "shifted_logit_normal"
  # Additional parameters for timestep sampling
  timestep_sampling_params: { }
 # -----------------------------------------------------------------------------
 # Hugging Face Hub Configuration
 # -----------------------------------------------------------------------------
 # Settings for uploading trained models to the Hugging Face Hub.
 hub:
  # Whether to push the trained model to the Hub
  push_to_hub: false
  # Repository ID on Hugging Face Hub (e.g., "username/my-ic-lora-model")
  # Required if push_to_hub is true
  hub_model_id: null
 # -----------------------------------------------------------------------------
 # Weights & Biases Configuration
 # -----------------------------------------------------------------------------
 # Settings for experiment tracking with W&B.
 wandb:
  # Enable W&B logging
  enabled: false
  # W&B project name
  project: "ltx-2-trainer"
  # W&B username or team (null uses default account)
  entity: null
  # Tags to help organize runs
  tags: [ "ltx2", "lora", "audio-inpainting", "audio-only" ]
  # Log validation media (video/audio) to W&B
  log_validation_videos: true
 # -----------------------------------------------------------------------------
 # General Configuration
 # -----------------------------------------------------------------------------
 # Global settings for the training run.
 # Random seed for reproducibility
 seed: 42
 # Directory to save outputs (checkpoints, validation videos, logs)
 output_dir: "outputs/audio_inpainting_lora"
@@ -1,343 +0,0 @@
 # =============================================================================
 # LTX-2 Audio Extension (Backward) LoRA Training Configuration
 # =============================================================================
 #
 # This configuration is for training LoRA adapters on the LTX-2 model for
 # backward audio extension. The model learns to generate audio content leading into existing audio
 # by conditioning on a suffix of existing audio latent timesteps.
 #
 # Suffix conditioning works by providing the last N audio latent timesteps as
 # clean conditioning signals during training — they receive no noise,
 # timestep=0, and are excluded from the loss. The model learns to generate
 # audio that seamlessly leads into the given suffix.
 #
 # This is an audio-only training mode — no video modality is configured.
 #
 # Use this configuration when you want to:
 #   - Train the model to generate preceding content for existing audio
 #   - Fine-tune audio temporal continuation capabilities
 #   - Create seamless audio extension models
 #
 # Dataset structure:
 #   preprocessed_data_root/
 #   ├── conditions/      # Text embeddings for each sample
 #   └── audio_latents/   # Audio latents (VAE-encoded audio)
 #
 # =============================================================================
 # -----------------------------------------------------------------------------
 # Model Configuration
 # -----------------------------------------------------------------------------
 # Specifies the base model to fine-tune and the training mode.
 model:
  # Path to the LTX-2 model checkpoint (.safetensors file)
  # This should be a local path to your downloaded model
  model_path: "path/to/ltx-2-model.safetensors"
  # Path to the text encoder model directory
  # For LTX-2, this is typically the Gemma-based text encoder
  text_encoder_path: "path/to/gemma-text-encoder"
  # Training mode: "lora" for efficient adapter training, "full" for full fine-tuning
  # LoRA is recommended for most use cases (faster, less memory, prevents overfitting)
  training_mode: "lora"
  # Optional: Path to resume training from a checkpoint
  # Can be a checkpoint file (.safetensors) or directory (uses latest checkpoint)
  load_checkpoint: null
 # -----------------------------------------------------------------------------
 # LoRA Configuration
 # -----------------------------------------------------------------------------
 # Controls the Low-Rank Adaptation parameters for efficient fine-tuning.
 lora:
  # Rank of the LoRA matrices (higher = more capacity but more parameters)
  # Typical values: 8, 16, 32, 64. Start with 32 for audio extension LoRA training.
  rank: 32
  # Alpha scaling factor (usually set equal to rank)
  # The effective scaling is alpha/rank, so alpha=rank means scaling of 1.0
  alpha: 32
  # Dropout probability for LoRA layers (0.0 = no dropout)
  # Can help with regularization if overfitting occurs
  dropout: 0.0
  # Which transformer modules to apply LoRA to
  # The LTX-2 transformer has separate attention and FFN blocks for video and audio:
  #
  # VIDEO MODULES (not used for audio-only modes):
  #   - attn1.to_k, attn1.to_q, attn1.to_v, attn1.to_out.0  (video self-attention)
  #   - attn2.to_k, attn2.to_q, attn2.to_v, attn2.to_out.0  (video cross-attention to text)
  #   - ff.net.0.proj, ff.net.2                             (video feed-forward)
  #
  # AUDIO MODULES:
  #   - audio_attn1.to_k, audio_attn1.to_q, audio_attn1.to_v, audio_attn1.to_out.0  (audio self-attention)
  #   - audio_attn2.to_k, audio_attn2.to_q, audio_attn2.to_v, audio_attn2.to_out.0  (audio cross-attention to text)
  #   - audio_ff.net.0.proj, audio_ff.net.2                                         (audio feed-forward)
  #
  # AUDIO-VIDEO CROSS-ATTENTION MODULES (not used for audio-only modes):
  #   - audio_to_video_attn.to_k, audio_to_video_attn.to_q, audio_to_video_attn.to_v, audio_to_video_attn.to_out.0
  #       (Q from video, K/V from audio - allows video to attend to audio features)
  #   - video_to_audio_attn.to_k, video_to_audio_attn.to_q, video_to_audio_attn.to_v, video_to_audio_attn.to_out.0
  #       (Q from audio, K/V from video - allows audio to attend to video features)
  #
  # For audio-only extension, we explicitly target audio modules.
  # Including audio FFN layers can increase the LoRA's capacity.
  target_modules:
    # Audio self-attention
    - "audio_attn1.to_k"
    - "audio_attn1.to_q"
    - "audio_attn1.to_v"
    - "audio_attn1.to_out.0"
    # Audio cross-attention to text
    - "audio_attn2.to_k"
    - "audio_attn2.to_q"
    - "audio_attn2.to_v"
    - "audio_attn2.to_out.0"
    # Audio feed-forward (often improves transformation quality)
    - "audio_ff.net.0.proj"
    - "audio_ff.net.2"
 # -----------------------------------------------------------------------------
 # Training Strategy Configuration
 # -----------------------------------------------------------------------------
 # Defines the backward audio extension training approach using the unified flexible
 # strategy. Suffix conditioning provides the last N audio latent timesteps as
 # clean conditioning, teaching the model to generate content leading into existing audio.
 training_strategy:
  name: "flexible"
  # Audio modality configuration (audio-only, no video)
  audio:
    # Whether the model generates audio (true) or uses it as frozen conditioning (false)
    is_generated: true
    # Directory name (within preprocessed_data_root) containing audio latents
    latents_dir: "audio_latents"
    # Conditions applied to the audio modality during training
    conditions:
      - type: suffix
        # Number of audio latent timesteps to use as conditioning suffix
        # Each audio latent timestep = 1 patchified token
        temporal_boundary: 8
        # Probability of applying suffix conditioning per training sample
        # At 1.0, all training samples use audio extension mode
        probability: 1.0
 # -----------------------------------------------------------------------------
 # Optimization Configuration
 # -----------------------------------------------------------------------------
 # Controls the training optimization parameters.
 optimization:
  # Learning rate for the optimizer
  # Typical range for LoRA: 1e-5 to 1e-4
  learning_rate: 2e-4
  # Total number of training steps
  steps: 3000
  # Batch size per GPU
  # Reduce if running out of memory
  batch_size: 1
  # Number of gradient accumulation steps
  # Effective batch size = batch_size * gradient_accumulation_steps * num_gpus
  gradient_accumulation_steps: 1
  # Maximum gradient norm for clipping (helps training stability)
  max_grad_norm: 1.0
  # Optimizer type: "adamw" (standard) or "adamw8bit" (memory-efficient)
  optimizer_type: "adamw"
  # Learning rate scheduler type
  # Options: "constant", "linear", "cosine", "cosine_with_restarts", "polynomial"
  scheduler_type: "linear"
  # Additional scheduler parameters (depends on scheduler_type)
  scheduler_params: { }
  # Enable gradient checkpointing to reduce memory usage
  # Recommended for training with limited GPU memory
  enable_gradient_checkpointing: true
 # -----------------------------------------------------------------------------
 # Acceleration Configuration
 # -----------------------------------------------------------------------------
 # Hardware acceleration and memory optimization settings.
 acceleration:
  # Mixed precision training mode
  # Options: "no" (fp32), "fp16" (half precision), "bf16" (bfloat16, recommended)
  mixed_precision_mode: "bf16"
  # Model quantization for reduced memory usage
  # Options: null (none), "int8-quanto", "int4-quanto", "int2-quanto", "fp8-quanto", "fp8uz-quanto"
  quantization: null
  # Load text encoder in 8-bit precision to save memory
  # Useful when GPU memory is limited
  load_text_encoder_in_8bit: false
  # Offload optimizer state to CPU during validation video sampling and restore it after.
  # Frees VRAM for the VAE decoder when optimizer state is large (full fine-tune, high-rank
  # LoRA). No effect under FSDP (sharded state).
  offload_optimizer_during_validation: false
 # -----------------------------------------------------------------------------
 # Data Configuration
 # -----------------------------------------------------------------------------
 # Specifies the training data location and loading parameters.
 data:
  # Root directory containing preprocessed training data
  # Should contain: conditions/ and audio_latents/ subdirectories
  preprocessed_data_root: "/path/to/preprocessed/data"
  # Number of worker processes for data loading
  # Used for parallel data loading to speed up data loading
  num_dataloader_workers: 2
 # -----------------------------------------------------------------------------
 # Validation Configuration
 # -----------------------------------------------------------------------------
 # Controls validation sampling during training.
 # NOTE: Validation sampling use simplified inference pipelines and prioritizes speed over
 # maximum quality. For production-quality inference, use `packages/ltx-pipelines`.
 validation:
  # Validation samples — each sample describes a self-contained generation request.
  # Each sample includes an audio suffix condition for backward audio extension.
  samples:
    - prompt: >-
        A warm and soothing piano melody with soft ambient textures, reminiscent of a quiet
        evening by the fireplace. Gentle reverb creates a sense of intimate space.
      conditions:
        - type: suffix
          audio: "/path/to/suffix_audio_1.wav"
          # Duration is in seconds; choose a value that covers a comparable audio context
          # to the training temporal_boundary measured in audio latent timesteps.
          duration: 1.0
    - prompt: >-
        Energetic electronic beats with pulsing synthesizer leads and crisp hi-hat patterns.
        Deep bass tones provide a driving rhythm underneath bright melodic arpeggios.
      conditions:
        - type: suffix
          audio: "/path/to/suffix_audio_2.wav"
          # Duration is in seconds; choose a value that covers a comparable audio context
          # to the training temporal_boundary measured in audio latent timesteps.
          duration: 1.0
  # Negative prompt to avoid unwanted artifacts
  negative_prompt: "worst quality, inconsistent motion, blurry, jittery, distorted"
  # Generation length control [width, height, frames]
  # With generate_video=false, width/height are unused; frames and frame_rate set audio duration.
  # Frames must satisfy: frames % 8 == 1 (e.g., 1, 9, 17, 25, 33, 41, 49, 57, 65, 73, 81, 89, ...)
  video_dims: [ 512, 512, 81 ]
  # Frame rate for generated videos
  frame_rate: 25.0
  # Random seed for reproducible validation outputs
  seed: 42
  # Number of denoising steps for validation inference
  # Higher values = better quality but slower generation
  inference_steps: 30
  # Generate validation videos every N training steps
  # Set to null to disable validation during training
  interval: 100
  # Classifier-free guidance scale
  # Higher values = stronger adherence to prompt but may introduce artifacts
  guidance_scale: 4.0
  # STG (Spatio-Temporal Guidance) parameters for improved video quality
  # STG is combined with CFG for better temporal coherence
  stg_scale: 1.0  # Recommended: 1.0 (0.0 disables STG)
  stg_blocks: [29]  # Recommended: single block 29
  stg_mode: "stg_av"  # "stg_av" skips both audio and video self-attention (suited to audio validation)
  # Whether to generate audio in validation samples
  # Enabled because this audio-only config generates audio
  generate_audio: true
  # Whether to generate video in validation samples
  # Disabled because no video modality is configured
  generate_video: false
  # Skip validation at the beginning of training (step 0)
  skip_initial_validation: false
 # -----------------------------------------------------------------------------
 # Checkpoint Configuration
 # -----------------------------------------------------------------------------
 # Controls model checkpoint saving during training.
 checkpoints:
  # Save a checkpoint every N steps
  # Set to null to disable intermediate checkpoints
  interval: 250
  # Number of most recent checkpoints to keep
  # Set to -1 to keep all checkpoints
  keep_last_n: 3
  # Precision to use when saving checkpoint weights
  # Options: "bfloat16" (default, smaller files) or "float32" (full precision)
  precision: "bfloat16"
 # -----------------------------------------------------------------------------
 # Flow Matching Configuration
 # -----------------------------------------------------------------------------
 # Parameters for the flow matching training objective.
 flow_matching:
  # Timestep sampling mode
  # "shifted_logit_normal" is recommended for LTX-2 models
  timestep_sampling_mode: "shifted_logit_normal"
  # Additional parameters for timestep sampling
  timestep_sampling_params: { }
 # -----------------------------------------------------------------------------
 # Hugging Face Hub Configuration
 # -----------------------------------------------------------------------------
 # Settings for uploading trained models to the Hugging Face Hub.
 hub:
  # Whether to push the trained model to the Hub
  push_to_hub: false
  # Repository ID on Hugging Face Hub (e.g., "username/my-ic-lora-model")
  # Required if push_to_hub is true
  hub_model_id: null
 # -----------------------------------------------------------------------------
 # Weights & Biases Configuration
 # -----------------------------------------------------------------------------
 # Settings for experiment tracking with W&B.
 wandb:
  # Enable W&B logging
  enabled: false
  # W&B project name
  project: "ltx-2-trainer"
  # W&B username or team (null uses default account)
  entity: null
  # Tags to help organize runs
  tags: [ "ltx2", "lora", "audio-suffix", "audio-only" ]
  # Log validation media (video/audio) to W&B
  log_validation_videos: true
 # -----------------------------------------------------------------------------
 # General Configuration
 # -----------------------------------------------------------------------------
 # Global settings for the training run.
 # Random seed for reproducibility
 seed: 42
 # Directory to save outputs (checkpoints, validation videos, logs)
 output_dir: "outputs/audio_suffix_lora"
@@ -1,342 +0,0 @@
 # =============================================================================
 # LTX-2 AV2AV IC-LoRA Training Configuration
 # =============================================================================
 #
 # This configuration is for training In-Context LoRA (IC-LoRA) adapters that
 # enable joint audio-video-to-audio-video transformations. IC-LoRA learns to
 # apply transformations to both the video and audio modalities simultaneously
 # by conditioning on paired reference video and audio.
 #
 # Both modalities use reference conditioning: pre-encoded reference latents
 # are concatenated to each modality's target sequence. Reference tokens
 # participate in bidirectional self-attention but receive no noise and are
 # excluded from the loss.
 #
 # Key differences from video-only IC-LoRA (v2v_ic_lora.yaml):
 #   - Both video AND audio have reference conditions
 #   - Requires preprocessed reference latents for BOTH modalities
 #   - LoRA targets all modules (video, audio, and cross-modal attention)
 #   - Validation uses both video and audio reference conditions
 #
 # Dataset structure:
 #   preprocessed_data_root/
 #   ├── latents/                 # Target video latents
 #   ├── audio_latents/           # Target audio latents
 #   ├── conditions/              # Text embeddings
 #   ├── reference_latents/       # Reference video latents (conditioning input)
 #   └── reference_audio_latents/ # Reference audio latents (conditioning input)
 #
 # Dataset metadata columns: video, audio, reference_video, reference_audio, caption
 #
 # =============================================================================
 # -----------------------------------------------------------------------------
 # Model Configuration
 # -----------------------------------------------------------------------------
 # Specifies the base model to fine-tune and the training mode.
 model:
  # Path to the LTX-2 model checkpoint (.safetensors file)
  # This should be a local path to your downloaded model
  model_path: "path/to/ltx-2-model.safetensors"
  # Path to the text encoder model directory
  # For LTX-2, this is typically the Gemma-based text encoder
  text_encoder_path: "path/to/gemma-text-encoder"
  # Training mode: "lora" for efficient adapter training, "full" for full fine-tuning
  # IC-LoRA reference conditioning is intended for LoRA adapter training.
  training_mode: "lora"
  # Optional: Path to resume training from a checkpoint
  # Can be a checkpoint file (.safetensors) or directory (uses latest checkpoint)
  load_checkpoint: null
 # -----------------------------------------------------------------------------
 # LoRA Configuration
 # -----------------------------------------------------------------------------
 # Controls the Low-Rank Adaptation parameters for efficient fine-tuning.
 lora:
  # Rank of the LoRA matrices (higher = more capacity but more parameters)
  # Typical values: 8, 16, 32, 64. Start with 16-32 for IC-LoRA.
  rank: 32
  # Alpha scaling factor (usually set equal to rank)
  # The effective scaling is alpha/rank, so alpha=rank means scaling of 1.0
  alpha: 32
  # Dropout probability for LoRA layers (0.0 = no dropout)
  # Can help with regularization if overfitting occurs
  dropout: 0.0
  # For AV2AV IC-LoRA, we target ALL modules — video, audio, and cross-modal attention.
  # Using short patterns matches all branches simultaneously.
  target_modules:
    # Attention layers (matches video, audio, and cross-modal branches)
    - "to_k"
    - "to_q"
    - "to_v"
    - "to_out.0"
 # -----------------------------------------------------------------------------
 # Training Strategy Configuration
 # -----------------------------------------------------------------------------
 # Defines the AV2AV IC-LoRA training approach using the unified flexible
 # strategy. Both video and audio modalities have reference conditioning,
 # enabling joint audiovisual transformations.
 training_strategy:
  name: "flexible"
  # Video modality configuration
  video:
    # Whether the model generates video (true) or uses it as frozen conditioning (false)
    is_generated: true
    # Directory name (within preprocessed_data_root) containing target video latents
    latents_dir: "latents"
    # Conditions applied to the video modality during training
    conditions:
      # Reference conditioning (IC-LoRA): concatenates pre-encoded reference video
      # latents to the target sequence
      - type: reference
        latents_dir: "reference_latents"
        probability: 1.0
  # Audio modality configuration
  audio:
    # Whether the model generates audio (true) or uses it as frozen conditioning (false)
    is_generated: true
    # Directory name (within preprocessed_data_root) containing target audio latents
    latents_dir: "audio_latents"
    # Conditions applied to the audio modality during training
    conditions:
      # Reference conditioning (IC-LoRA): concatenates pre-encoded reference audio
      # latents to the target sequence
      - type: reference
        latents_dir: "reference_audio_latents"
        probability: 1.0
 # -----------------------------------------------------------------------------
 # Optimization Configuration
 # -----------------------------------------------------------------------------
 # Controls the training optimization parameters.
 optimization:
  # Learning rate for the optimizer
  # Typical range for LoRA: 1e-5 to 1e-4
  learning_rate: 2e-4
  # Total number of training steps
  steps: 3000
  # Batch size per GPU
  # Reduce if running out of memory
  batch_size: 1
  # Number of gradient accumulation steps
  # Effective batch size = batch_size * gradient_accumulation_steps * num_gpus
  gradient_accumulation_steps: 1
  # Maximum gradient norm for clipping (helps training stability)
  max_grad_norm: 1.0
  # Optimizer type: "adamw" (standard) or "adamw8bit" (memory-efficient)
  optimizer_type: "adamw"
  # Learning rate scheduler type
  # Options: "constant", "linear", "cosine", "cosine_with_restarts", "polynomial"
  scheduler_type: "linear"
  # Additional scheduler parameters (depends on scheduler_type)
  scheduler_params: { }
  # Enable gradient checkpointing to reduce memory usage
  # Recommended for training with limited GPU memory
  enable_gradient_checkpointing: true
 # -----------------------------------------------------------------------------
 # Acceleration Configuration
 # -----------------------------------------------------------------------------
 # Hardware acceleration and memory optimization settings.
 acceleration:
  # Mixed precision training mode
  # Options: "no" (fp32), "fp16" (half precision), "bf16" (bfloat16, recommended)
  mixed_precision_mode: "bf16"
  # Model quantization for reduced memory usage
  # Options: null (none), "int8-quanto", "int4-quanto", "int2-quanto", "fp8-quanto", "fp8uz-quanto"
  quantization: null
  # Load text encoder in 8-bit precision to save memory
  # Useful when GPU memory is limited
  load_text_encoder_in_8bit: false
  # Offload optimizer state to CPU during validation video sampling and restore it after.
  # Frees VRAM for the VAE decoder when optimizer state is large (full fine-tune, high-rank
  # LoRA). No effect under FSDP (sharded state).
  offload_optimizer_during_validation: false
 # -----------------------------------------------------------------------------
 # Data Configuration
 # -----------------------------------------------------------------------------
 # Specifies the training data location and loading parameters.
 data:
  # Root directory containing preprocessed training data
  # Should contain: latents/, audio_latents/, conditions/, reference_latents/, and reference_audio_latents/
  preprocessed_data_root: "/path/to/preprocessed/data"
  # Number of worker processes for data loading
  # Used for parallel data loading to speed up data loading
  num_dataloader_workers: 2
 # -----------------------------------------------------------------------------
 # Validation Configuration
 # -----------------------------------------------------------------------------
 # Controls validation sampling during training.
 # NOTE: Validation sampling use simplified inference pipelines and prioritizes speed over
 # maximum quality. For production-quality inference, use `packages/ltx-pipelines`.
 validation:
  # Validation samples — each sample describes a self-contained generation request.
  # For AV2AV IC-LoRA, each sample includes reference video and reference audio conditions.
  samples:
    - prompt: >-
        A man in a casual blue jacket walks along a winding path through a lush green park on a
        bright sunny afternoon. Tall oak trees line the pathway, their leaves rustling gently in
        the breeze. Dappled sunlight creates shifting patterns on the ground as he strolls at a
        relaxed pace, occasionally looking up at the scenery around him. The audio captures
        footsteps on gravel, birds singing in the trees, distant children playing, and the soft
        whisper of wind through the foliage.
      conditions:
        - type: reference
          video: "/path/to/reference_video_1.mp4"
          downscale_factor: 1
          temporal_scale_factor: 1
          include_in_output: true
        - type: reference
          audio: "/path/to/reference_audio_1.wav"
    - prompt: >-
        A fluffy orange tabby cat sits perfectly still on a wooden windowsill, its green eyes
        intently tracking small birds hopping on a branch just outside the glass. The cat's ears
        twitch and rotate, following every movement. Warm afternoon light illuminates its fur,
        creating a soft golden glow. Behind the cat, a cozy living room with a bookshelf and
        houseplants is visible. The audio features gentle purring, occasional soft meows, muffled
        bird chirps through the window, and quiet ambient room sounds.
      conditions:
        - type: reference
          video: "/path/to/reference_video_2.mp4"
          downscale_factor: 1
          temporal_scale_factor: 1
          include_in_output: true
        - type: reference
          audio: "/path/to/reference_audio_2.wav"
  # Negative prompt to avoid unwanted artifacts
  negative_prompt: "worst quality, inconsistent motion, blurry, jittery, distorted"
  # Output video dimensions [width, height, frames]
  # Width and height must be divisible by 32
  # Frames must satisfy: frames % 8 == 1 (e.g., 1, 9, 17, 25, 33, 41, 49, 57, 65, 73, 81, 89, ...)
  video_dims: [ 512, 512, 81 ]
  # Frame rate for generated videos
  frame_rate: 25.0
  # Random seed for reproducible validation outputs
  seed: 42
  # Number of denoising steps for validation inference
  # Higher values = better quality but slower generation
  inference_steps: 30
  # Generate validation videos every N training steps
  # Set to null to disable validation during training
  interval: 100
  # Classifier-free guidance scale
  # Higher values = stronger adherence to prompt but may introduce artifacts
  guidance_scale: 4.0
  # STG (Spatio-Temporal Guidance) parameters for improved video quality
  # STG is combined with CFG for better temporal coherence
  stg_scale: 1.0  # Recommended: 1.0 (0.0 disables STG)
  stg_blocks: [29]  # Recommended: single block 29
  stg_mode: "stg_av"  # Both video and audio modalities are trained
  # Whether to generate audio in validation samples
  # Can be enabled even when not training the audio branch
  generate_audio: true
  # Skip validation at the beginning of training (step 0)
  skip_initial_validation: false
 # -----------------------------------------------------------------------------
 # Checkpoint Configuration
 # -----------------------------------------------------------------------------
 # Controls model checkpoint saving during training.
 checkpoints:
  # Save a checkpoint every N steps
  # Set to null to disable intermediate checkpoints
  interval: 250
  # Number of most recent checkpoints to keep
  # Set to -1 to keep all checkpoints
  keep_last_n: 3
  # Precision to use when saving checkpoint weights
  # Options: "bfloat16" (default, smaller files) or "float32" (full precision)
  precision: "bfloat16"
 # -----------------------------------------------------------------------------
 # Flow Matching Configuration
 # -----------------------------------------------------------------------------
 # Parameters for the flow matching training objective.
 flow_matching:
  # Timestep sampling mode
  # "shifted_logit_normal" is recommended for LTX-2 models
  timestep_sampling_mode: "shifted_logit_normal"
  # Additional parameters for timestep sampling
  timestep_sampling_params: { }
 # -----------------------------------------------------------------------------
 # Hugging Face Hub Configuration
 # -----------------------------------------------------------------------------
 # Settings for uploading trained models to the Hugging Face Hub.
 hub:
  # Whether to push the trained model to the Hub
  push_to_hub: false
  # Repository ID on Hugging Face Hub (e.g., "username/my-ic-lora-model")
  # Required if push_to_hub is true
  hub_model_id: null
 # -----------------------------------------------------------------------------
 # Weights & Biases Configuration
 # -----------------------------------------------------------------------------
 # Settings for experiment tracking with W&B.
 wandb:
  # Enable W&B logging
  enabled: false
  # W&B project name
  project: "ltx-2-trainer"
  # W&B username or team (null uses default account)
  entity: null
  # Tags to help organize runs
  tags: [ "ltx2", "ic-lora", "av2av" ]
  # Log validation media (video/audio) to W&B
  log_validation_videos: true
 # -----------------------------------------------------------------------------
 # General Configuration
 # -----------------------------------------------------------------------------
 # Global settings for the training run.
 # Random seed for reproducibility
 seed: 42
 # Directory to save outputs (checkpoints, validation videos, logs)
 output_dir: "outputs/av2av_ic_lora"
@@ -1,348 +0,0 @@
 # =============================================================================
 # LTX-2 Image-to-Video LoRA Training Configuration
 # =============================================================================
 #
 # This configuration is for training LoRA adapters on the LTX-2 model for
 # image-to-video generation. The model learns to generate videos conditioned
 # on a starting image (first frame), with optional audio generation.
 #
 # First-frame conditioning works by providing the first frame as a clean
 # conditioning signal during training — it receives no noise, timestep=0,
 # and is excluded from the loss. This teaches the model to animate from
 # a given image.
 #
 # Use this configuration when you want to:
 #   - Train the model to generate videos starting from a given image
 #   - Fine-tune image-to-video capabilities on custom datasets
 #   - Create image animation models with optional audio
 #
 # Dataset structure:
 #   preprocessed_data_root/
 #   ├── latents/        # Video latents (VAE-encoded videos)
 #   ├── conditions/     # Text embeddings for each video
 #   └── audio_latents/  # Audio latents (VAE-encoded audio)
 #
 # =============================================================================
 # -----------------------------------------------------------------------------
 # Model Configuration
 # -----------------------------------------------------------------------------
 # Specifies the base model to fine-tune and the training mode.
 model:
  # Path to the LTX-2 model checkpoint (.safetensors file)
  # This should be a local path to your downloaded model
  model_path: "path/to/ltx-2-model.safetensors"
  # Path to the text encoder model directory
  # For LTX-2, this is typically the Gemma-based text encoder
  text_encoder_path: "path/to/gemma-text-encoder"
  # Training mode: "lora" for efficient adapter training, "full" for full fine-tuning
  # LoRA is recommended for most use cases (faster, less memory, prevents overfitting)
  training_mode: "lora"
  # Optional: Path to resume training from a checkpoint
  # Can be a checkpoint file (.safetensors) or directory (uses latest checkpoint)
  load_checkpoint: null
 # -----------------------------------------------------------------------------
 # LoRA Configuration
 # -----------------------------------------------------------------------------
 # Controls the Low-Rank Adaptation parameters for efficient fine-tuning.
 lora:
  # Rank of the LoRA matrices (higher = more capacity but more parameters)
  # Typical values: 8, 16, 32, 64. Start with 32 for general fine-tuning.
  rank: 32
  # Alpha scaling factor (usually set equal to rank)
  # The effective scaling is alpha/rank, so alpha=rank means scaling of 1.0
  alpha: 32
  # Dropout probability for LoRA layers (0.0 = no dropout)
  # Can help with regularization if overfitting occurs
  dropout: 0.0
  # Which transformer modules to apply LoRA to
  # The LTX-2 transformer has separate attention and FFN blocks for video and audio:
  #
  # VIDEO MODULES:
  #   - attn1.to_k, attn1.to_q, attn1.to_v, attn1.to_out.0  (video self-attention)
  #   - attn2.to_k, attn2.to_q, attn2.to_v, attn2.to_out.0  (video cross-attention to text)
  #   - ff.net.0.proj, ff.net.2                             (video feed-forward)
  #
  # AUDIO MODULES:
  #   - audio_attn1.to_k, audio_attn1.to_q, audio_attn1.to_v, audio_attn1.to_out.0  (audio self-attention)
  #   - audio_attn2.to_k, audio_attn2.to_q, audio_attn2.to_v, audio_attn2.to_out.0  (audio cross-attention to text)
  #   - audio_ff.net.0.proj, audio_ff.net.2                                         (audio feed-forward)
  #
  # AUDIO-VIDEO CROSS-ATTENTION MODULES (for cross-modal interaction):
  #   - audio_to_video_attn.to_k, audio_to_video_attn.to_q, audio_to_video_attn.to_v, audio_to_video_attn.to_out.0
  #       (Q from video, K/V from audio - allows video to attend to audio features)
  #   - video_to_audio_attn.to_k, video_to_audio_attn.to_q, video_to_audio_attn.to_v, video_to_audio_attn.to_out.0
  #       (Q from audio, K/V from video - allows audio to attend to video features)
  #
  # Using short patterns like "to_k" matches ALL attention modules (video, audio, and cross-modal).
  # For audio-video training, this is the recommended approach.
  target_modules:
    # Attention layers (matches both video and audio branches)
    - "to_k"
    - "to_q"
    - "to_v"
    - "to_out.0"
    # Uncomment below to also train feed-forward layers (can increase the LoRA's capacity):
    # - "ff.net.0.proj"
    # - "ff.net.2"
    # - "audio_ff.net.0.proj"
    # - "audio_ff.net.2"
 # -----------------------------------------------------------------------------
 # Training Strategy Configuration
 # -----------------------------------------------------------------------------
 # Defines the image-to-video training approach using the unified flexible strategy.
 # First-frame conditioning provides the first frame as clean conditioning signal
 # during training, teaching the model to animate from a given image.
 training_strategy:
  # Strategy name: "flexible" for the unified conditioning framework
  # Supports all training modes (T2V, I2V, V2V, A2V, V2A, etc.) through
  # modality-specific configuration blocks.
  name: "flexible"
  # Video modality configuration
  video:
    # Whether the model generates video (true) or uses it as frozen conditioning (false)
    is_generated: true
    # Directory name (within preprocessed_data_root) containing video latents
    latents_dir: "latents"
    # Conditions applied to the video modality during training
    # First-frame conditioning: the first frame of each video is provided as a clean
    # conditioning signal (no noise, timestep=0, excluded from loss)
    conditions:
      - type: first_frame
        # Probability of applying first-frame conditioning per training sample
        # At 0.5, half the training samples use I2V mode, half use pure T2V
        # Higher values improve I2V quality but may reduce T2V diversity
        probability: 0.5
  # Audio modality configuration
  audio:
    # Whether the model generates audio (true) or uses it as frozen conditioning (false)
    is_generated: true
    # Directory name (within preprocessed_data_root) containing audio latents
    latents_dir: "audio_latents"
 # -----------------------------------------------------------------------------
 # Optimization Configuration
 # -----------------------------------------------------------------------------
 # Controls the training optimization parameters.
 optimization:
  # Learning rate for the optimizer
  # Typical range for LoRA: 1e-5 to 1e-4
  learning_rate: 1e-4
  # Total number of training steps
  steps: 2000
  # Batch size per GPU
  # Reduce if running out of memory
  batch_size: 1
  # Number of gradient accumulation steps
  # Effective batch size = batch_size * gradient_accumulation_steps * num_gpus
  gradient_accumulation_steps: 1
  # Maximum gradient norm for clipping (helps training stability)
  max_grad_norm: 1.0
  # Optimizer type: "adamw" (standard) or "adamw8bit" (memory-efficient)
  optimizer_type: "adamw"
  # Learning rate scheduler type
  # Options: "constant", "linear", "cosine", "cosine_with_restarts", "polynomial"
  scheduler_type: "linear"
  # Additional scheduler parameters (depends on scheduler_type)
  scheduler_params: { }
  # Enable gradient checkpointing to reduce memory usage
  # Recommended for training with limited GPU memory
  enable_gradient_checkpointing: true
 # -----------------------------------------------------------------------------
 # Acceleration Configuration
 # -----------------------------------------------------------------------------
 # Hardware acceleration and memory optimization settings.
 acceleration:
  # Mixed precision training mode
  # Options: "no" (fp32), "fp16" (half precision), "bf16" (bfloat16, recommended)
  mixed_precision_mode: "bf16"
  # Model quantization for reduced memory usage
  # Options: null (none), "int8-quanto", "int4-quanto", "int2-quanto", "fp8-quanto", "fp8uz-quanto"
  quantization: null
  # Load text encoder in 8-bit precision to save memory
  # Useful when GPU memory is limited
  load_text_encoder_in_8bit: false
  # Offload optimizer state to CPU during validation video sampling and restore it after.
  # Frees VRAM for the VAE decoder when optimizer state is large (full fine-tune, high-rank
  # LoRA). No effect under FSDP (sharded state).
  offload_optimizer_during_validation: false
 # -----------------------------------------------------------------------------
 # Data Configuration
 # -----------------------------------------------------------------------------
 # Specifies the training data location and loading parameters.
 data:
  # Root directory containing preprocessed training data
  # Should contain: latents/, conditions/, and audio_latents/
  preprocessed_data_root: "/path/to/preprocessed/data"
  # Number of worker processes for data loading
  # Used for parallel data loading to speed up data loading
  num_dataloader_workers: 2
 # -----------------------------------------------------------------------------
 # Validation Configuration
 # -----------------------------------------------------------------------------
 # Controls validation sampling during training.
 # NOTE: Validation sampling use simplified inference pipelines and prioritizes speed over
 # maximum quality. For production-quality inference, use `packages/ltx-pipelines`.
 validation:
  # Validation samples — each sample describes a self-contained generation request.
  # Use 'conditions' to add conditioning (first_frame, prefix, suffix, reference, video_to_audio, etc.)
  # See docs/configuration-reference.md#validation-condition-types for the full list of condition types.
  samples:
    - prompt: >-
        A woman with long brown hair sits at a wooden desk in a cozy home office, typing on a
        laptop while occasionally glancing at notes beside her. Soft natural light streams through
        a large window, casting warm shadows across the room. She pauses to take a sip from a
        ceramic mug, then continues working with focused concentration. The audio captures the
        gentle clicking of keyboard keys, the soft rustle of papers, and ambient room tone with
        occasional distant bird chirps from outside.
      conditions:
        - type: first_frame
          image_or_video: "/path/to/conditioning_image_1.png"
    - prompt: >-
        A chef in a white uniform stands in a professional kitchen, carefully plating a gourmet
        dish with precise movements. Steam rises from freshly cooked vegetables as he arranges
        them with tweezers. The stainless steel surfaces gleam under bright overhead lights, and
        various pots simmer on the stove behind him. The audio features the sizzling of pans,
        the clinking of utensils against plates, and the ambient hum of kitchen ventilation.
      conditions:
        - type: first_frame
          image_or_video: "/path/to/conditioning_image_2.png"
  # Negative prompt to avoid unwanted artifacts
  negative_prompt: "worst quality, inconsistent motion, blurry, jittery, distorted"
  # Output video dimensions [width, height, frames]
  # Width and height must be divisible by 32
  # Frames must satisfy: frames % 8 == 1 (e.g., 1, 9, 17, 25, 33, 41, 49, 57, 65, 73, 81, 89, ...)
  video_dims: [ 576, 576, 89 ]
  # Frame rate for generated videos
  frame_rate: 25.0
  # Random seed for reproducible validation outputs
  seed: 42
  # Number of denoising steps for validation inference
  # Higher values = better quality but slower generation
  inference_steps: 30
  # Generate validation videos every N training steps
  # Set to null to disable validation during training
  interval: 100
  # Classifier-free guidance scale
  # Higher values = stronger adherence to prompt but may introduce artifacts
  guidance_scale: 4.0
  # STG (Spatio-Temporal Guidance) parameters for improved video quality
  # STG is combined with CFG for better temporal coherence
  stg_scale: 1.0  # Recommended: 1.0 (0.0 disables STG)
  stg_blocks: [29]  # Recommended: single block 29
  stg_mode: "stg_av"  # "stg_av" perturbs both audio and video, "stg_v" video only
  # Whether to generate audio in validation samples
  # Independent of training_strategy.audio.is_generated - you can generate audio
  # in validation even when not training the audio branch
  generate_audio: true
  # Skip validation at the beginning of training (step 0)
  skip_initial_validation: false
 # -----------------------------------------------------------------------------
 # Checkpoint Configuration
 # -----------------------------------------------------------------------------
 # Controls model checkpoint saving during training.
 checkpoints:
  # Save a checkpoint every N steps
  # Set to null to disable intermediate checkpoints
  interval: 250
  # Number of most recent checkpoints to keep
  # Set to -1 to keep all checkpoints
  keep_last_n: -1
  # Precision to use when saving checkpoint weights
  # Options: "bfloat16" (default, smaller files) or "float32" (full precision)
  precision: "bfloat16"
 # -----------------------------------------------------------------------------
 # Flow Matching Configuration
 # -----------------------------------------------------------------------------
 # Parameters for the flow matching training objective.
 flow_matching:
  # Timestep sampling mode
  # "shifted_logit_normal" is recommended for LTX-2 models
  timestep_sampling_mode: "shifted_logit_normal"
  # Additional parameters for timestep sampling
  timestep_sampling_params: { }
 # -----------------------------------------------------------------------------
 # Hugging Face Hub Configuration
 # -----------------------------------------------------------------------------
 # Settings for uploading trained models to the Hugging Face Hub.
 hub:
  # Whether to push the trained model to the Hub
  push_to_hub: false
  # Repository ID on Hugging Face Hub (e.g., "username/my-lora-model")
  # Required if push_to_hub is true
  hub_model_id: null
 # -----------------------------------------------------------------------------
 # Weights & Biases Configuration
 # -----------------------------------------------------------------------------
 # Settings for experiment tracking with W&B.
 wandb:
  # Enable W&B logging
  enabled: false
  # W&B project name
  project: "ltx-2-trainer"
  # W&B username or team (null uses default account)
  entity: null
  # Tags to help organize runs
  tags: [ "ltx2", "lora", "i2v" ]
  # Log validation media (video/audio) to W&B
  log_validation_videos: true
 # -----------------------------------------------------------------------------
 # General Configuration
 # -----------------------------------------------------------------------------
 # Global settings for the training run.
 # Random seed for reproducibility
 seed: 42
 # Directory to save outputs (checkpoints, validation videos, logs)
 output_dir: "outputs/i2v_lora"
@@ -1,317 +0,0 @@
 # =============================================================================
 # LTX-2 Text-to-Audio LoRA Training Configuration
 # =============================================================================
 #
 # This configuration is for training LoRA adapters on the LTX-2 model for
 # text-to-audio generation. The model learns to generate audio from text
 # prompts without any additional conditioning.
 #
 # This is the simplest audio-only training mode — no reference audio, no
 # video modality. Only the audio branch of the transformer is trained.
 #
 # Use this configuration when you want to:
 #   - Fine-tune audio generation for specific sound styles or domains
 #   - Train custom audio generation capabilities
 #   - Create audio LoRAs that can be combined with video LoRAs
 #
 # Dataset structure:
 #   preprocessed_data_root/
 #   ├── conditions/      # Text embeddings for each sample
 #   └── audio_latents/   # Audio latents (VAE-encoded audio)
 #
 # =============================================================================
 # -----------------------------------------------------------------------------
 # Model Configuration
 # -----------------------------------------------------------------------------
 # Specifies the base model to fine-tune and the training mode.
 model:
  # Path to the LTX-2 model checkpoint (.safetensors file)
  # This should be a local path to your downloaded model
  model_path: "path/to/ltx-2-model.safetensors"
  # Path to the text encoder model directory
  # For LTX-2, this is typically the Gemma-based text encoder
  text_encoder_path: "path/to/gemma-text-encoder"
  # Training mode: "lora" for efficient adapter training, "full" for full fine-tuning
  # LoRA is recommended for most use cases (faster, less memory, prevents overfitting)
  training_mode: "lora"
  # Optional: Path to resume training from a checkpoint
  # Can be a checkpoint file (.safetensors) or directory (uses latest checkpoint)
  load_checkpoint: null
 # -----------------------------------------------------------------------------
 # LoRA Configuration
 # -----------------------------------------------------------------------------
 # Controls the Low-Rank Adaptation parameters for efficient fine-tuning.
 lora:
  # Rank of the LoRA matrices (higher = more capacity but more parameters)
  # Typical values: 8, 16, 32, 64. Start with 32 for general audio LoRA training.
  rank: 32
  # Alpha scaling factor (usually set equal to rank)
  # The effective scaling is alpha/rank, so alpha=rank means scaling of 1.0
  alpha: 32
  # Dropout probability for LoRA layers (0.0 = no dropout)
  # Can help with regularization if overfitting occurs
  dropout: 0.0
  # Which transformer modules to apply LoRA to
  # The LTX-2 transformer has separate attention and FFN blocks for video and audio:
  #
  # VIDEO MODULES (not used for audio-only modes):
  #   - attn1.to_k, attn1.to_q, attn1.to_v, attn1.to_out.0  (video self-attention)
  #   - attn2.to_k, attn2.to_q, attn2.to_v, attn2.to_out.0  (video cross-attention to text)
  #   - ff.net.0.proj, ff.net.2                             (video feed-forward)
  #
  # AUDIO MODULES:
  #   - audio_attn1.to_k, audio_attn1.to_q, audio_attn1.to_v, audio_attn1.to_out.0  (audio self-attention)
  #   - audio_attn2.to_k, audio_attn2.to_q, audio_attn2.to_v, audio_attn2.to_out.0  (audio cross-attention to text)
  #   - audio_ff.net.0.proj, audio_ff.net.2                                         (audio feed-forward)
  #
  # AUDIO-VIDEO CROSS-ATTENTION MODULES (not used for audio-only modes):
  #   - audio_to_video_attn.to_k, audio_to_video_attn.to_q, audio_to_video_attn.to_v, audio_to_video_attn.to_out.0
  #       (Q from video, K/V from audio - allows video to attend to audio features)
  #   - video_to_audio_attn.to_k, video_to_audio_attn.to_q, video_to_audio_attn.to_v, video_to_audio_attn.to_out.0
  #       (Q from audio, K/V from video - allows audio to attend to video features)
  #
  # For audio-only training, we explicitly target audio modules.
  # Including audio FFN layers can increase the LoRA's capacity.
  target_modules:
    # Audio self-attention
    - "audio_attn1.to_k"
    - "audio_attn1.to_q"
    - "audio_attn1.to_v"
    - "audio_attn1.to_out.0"
    # Audio cross-attention to text
    - "audio_attn2.to_k"
    - "audio_attn2.to_q"
    - "audio_attn2.to_v"
    - "audio_attn2.to_out.0"
    # Audio feed-forward (often improves transformation quality)
    - "audio_ff.net.0.proj"
    - "audio_ff.net.2"
 # -----------------------------------------------------------------------------
 # Training Strategy Configuration
 # -----------------------------------------------------------------------------
 # Defines the text-to-audio training approach using the unified flexible
 # strategy. Audio-only training with no additional conditions — the model
 # learns to generate audio purely from text prompts.
 training_strategy:
  name: "flexible"
  # Audio modality configuration (audio-only, no video)
  audio:
    # Whether the model generates audio (true) or uses it as frozen conditioning (false)
    is_generated: true
    # Directory name (within preprocessed_data_root) containing audio latents
    latents_dir: "audio_latents"
 # -----------------------------------------------------------------------------
 # Optimization Configuration
 # -----------------------------------------------------------------------------
 # Controls the training optimization parameters.
 optimization:
  # Learning rate for the optimizer
  # Typical range for LoRA: 1e-5 to 1e-4
  learning_rate: 2e-4
  # Total number of training steps
  steps: 3000
  # Batch size per GPU
  # Reduce if running out of memory
  batch_size: 1
  # Number of gradient accumulation steps
  # Effective batch size = batch_size * gradient_accumulation_steps * num_gpus
  gradient_accumulation_steps: 1
  # Maximum gradient norm for clipping (helps training stability)
  max_grad_norm: 1.0
  # Optimizer type: "adamw" (standard) or "adamw8bit" (memory-efficient)
  optimizer_type: "adamw"
  # Learning rate scheduler type
  # Options: "constant", "linear", "cosine", "cosine_with_restarts", "polynomial"
  scheduler_type: "linear"
  # Additional scheduler parameters (depends on scheduler_type)
  scheduler_params: { }
  # Enable gradient checkpointing to reduce memory usage
  # Recommended for training with limited GPU memory
  enable_gradient_checkpointing: true
 # -----------------------------------------------------------------------------
 # Acceleration Configuration
 # -----------------------------------------------------------------------------
 # Hardware acceleration and memory optimization settings.
 acceleration:
  # Mixed precision training mode
  # Options: "no" (fp32), "fp16" (half precision), "bf16" (bfloat16, recommended)
  mixed_precision_mode: "bf16"
  # Model quantization for reduced memory usage
  # Options: null (none), "int8-quanto", "int4-quanto", "int2-quanto", "fp8-quanto", "fp8uz-quanto"
  quantization: null
  # Load text encoder in 8-bit precision to save memory
  # Useful when GPU memory is limited
  load_text_encoder_in_8bit: false
  # Offload optimizer state to CPU during validation video sampling and restore it after.
  # Frees VRAM for the VAE decoder when optimizer state is large (full fine-tune, high-rank
  # LoRA). No effect under FSDP (sharded state).
  offload_optimizer_during_validation: false
 # -----------------------------------------------------------------------------
 # Data Configuration
 # -----------------------------------------------------------------------------
 # Specifies the training data location and loading parameters.
 data:
  # Root directory containing preprocessed training data
  # Should contain: conditions/ and audio_latents/ subdirectories
  preprocessed_data_root: "/path/to/preprocessed/data"
  # Number of worker processes for data loading
  # Used for parallel data loading to speed up data loading
  num_dataloader_workers: 2
 # -----------------------------------------------------------------------------
 # Validation Configuration
 # -----------------------------------------------------------------------------
 # Controls validation sampling during training.
 # NOTE: Validation sampling use simplified inference pipelines and prioritizes speed over
 # maximum quality. For production-quality inference, use `packages/ltx-pipelines`.
 validation:
  # Validation samples — each sample describes a self-contained generation request.
  # Text-to-audio validation samples do not need additional conditions.
  samples:
    - prompt: >-
        A warm and soothing piano melody with soft ambient textures, reminiscent of a quiet
        evening by the fireplace. Gentle reverb creates a sense of intimate space.
    - prompt: >-
        Energetic electronic beats with pulsing synthesizer leads and crisp hi-hat patterns.
        Deep bass tones provide a driving rhythm underneath bright melodic arpeggios.
  # Negative prompt to avoid unwanted artifacts
  negative_prompt: "worst quality, inconsistent motion, blurry, jittery, distorted"
  # Generation length control [width, height, frames]
  # With generate_video=false, width/height are unused; frames and frame_rate set audio duration.
  # Frames must satisfy: frames % 8 == 1 (e.g., 1, 9, 17, 25, 33, 41, 49, 57, 65, 73, 81, 89, ...)
  video_dims: [ 512, 512, 81 ]
  # Frame rate for generated videos
  frame_rate: 25.0
  # Random seed for reproducible validation outputs
  seed: 42
  # Number of denoising steps for validation inference
  # Higher values = better quality but slower generation
  inference_steps: 30
  # Generate validation videos every N training steps
  # Set to null to disable validation during training
  interval: 100
  # Classifier-free guidance scale
  # Higher values = stronger adherence to prompt but may introduce artifacts
  guidance_scale: 4.0
  # STG (Spatio-Temporal Guidance) parameters for improved video quality
  # STG is combined with CFG for better temporal coherence
  stg_scale: 1.0  # Recommended: 1.0 (0.0 disables STG)
  stg_blocks: [29]  # Recommended: single block 29
  stg_mode: "stg_av"  # "stg_av" skips both audio and video self-attention (suited to audio validation)
  # Whether to generate audio in validation samples
  # Enabled because this audio-only config generates audio
  generate_audio: true
  # Whether to generate video in validation samples
  # Disabled because no video modality is configured
  generate_video: false
  # Skip validation at the beginning of training (step 0)
  skip_initial_validation: false
 # -----------------------------------------------------------------------------
 # Checkpoint Configuration
 # -----------------------------------------------------------------------------
 # Controls model checkpoint saving during training.
 checkpoints:
  # Save a checkpoint every N steps
  # Set to null to disable intermediate checkpoints
  interval: 250
  # Number of most recent checkpoints to keep
  # Set to -1 to keep all checkpoints
  keep_last_n: 3
  # Precision to use when saving checkpoint weights
  # Options: "bfloat16" (default, smaller files) or "float32" (full precision)
  precision: "bfloat16"
 # -----------------------------------------------------------------------------
 # Flow Matching Configuration
 # -----------------------------------------------------------------------------
 # Parameters for the flow matching training objective.
 flow_matching:
  # Timestep sampling mode
  # "shifted_logit_normal" is recommended for LTX-2 models
  timestep_sampling_mode: "shifted_logit_normal"
  # Additional parameters for timestep sampling
  timestep_sampling_params: { }
 # -----------------------------------------------------------------------------
 # Hugging Face Hub Configuration
 # -----------------------------------------------------------------------------
 # Settings for uploading trained models to the Hugging Face Hub.
 hub:
  # Whether to push the trained model to the Hub
  push_to_hub: false
  # Repository ID on Hugging Face Hub (e.g., "username/my-ic-lora-model")
  # Required if push_to_hub is true
  hub_model_id: null
 # -----------------------------------------------------------------------------
 # Weights & Biases Configuration
 # -----------------------------------------------------------------------------
 # Settings for experiment tracking with W&B.
 wandb:
  # Enable W&B logging
  enabled: false
  # W&B project name
  project: "ltx-2-trainer"
  # W&B username or team (null uses default account)
  entity: null
  # Tags to help organize runs
  tags: [ "ltx2", "lora", "t2a", "audio-only" ]
  # Log validation media (video/audio) to W&B
  log_validation_videos: true
 # -----------------------------------------------------------------------------
 # General Configuration
 # -----------------------------------------------------------------------------
 # Global settings for the training run.
 # Random seed for reproducibility
 seed: 42
 # Directory to save outputs (checkpoints, validation videos, logs)
 output_dir: "outputs/t2a_lora"
@@ -1,327 +0,0 @@
 # =============================================================================
 # LTX-2 Text-to-Video LoRA Training Configuration
 # =============================================================================
 #
 # This configuration is for training LoRA adapters on the LTX-2 model for
 # text-to-video generation with joint audio-video support.
 #
 # Use this configuration when you want to:
 #   - Fine-tune LTX-2 on your own video dataset
 #   - Train joint audio-video generation from text prompts
 #   - Create custom video generation styles or audiovisual concepts
 #
 # Dataset structure:
 #   preprocessed_data_root/
 #   ├── latents/        # Video latents (VAE-encoded videos)
 #   ├── conditions/     # Text embeddings for each video
 #   └── audio_latents/  # Audio latents (VAE-encoded audio)
 #
 # =============================================================================
 # -----------------------------------------------------------------------------
 # Model Configuration
 # -----------------------------------------------------------------------------
 # Specifies the base model to fine-tune and the training mode.
 model:
  # Path to the LTX-2 model checkpoint (.safetensors file)
  # This should be a local path to your downloaded model
  model_path: "path/to/ltx-2-model.safetensors"
  # Path to the text encoder model directory
  # For LTX-2, this is typically the Gemma-based text encoder
  text_encoder_path: "path/to/gemma-text-encoder"
  # Training mode: "lora" for efficient adapter training, "full" for full fine-tuning
  # LoRA is recommended for most use cases (faster, less memory, prevents overfitting)
  training_mode: "lora"
  # Optional: Path to resume training from a checkpoint
  # Can be a checkpoint file (.safetensors) or directory (uses latest checkpoint)
  load_checkpoint: null
 # -----------------------------------------------------------------------------
 # LoRA Configuration
 # -----------------------------------------------------------------------------
 # Controls the Low-Rank Adaptation parameters for efficient fine-tuning.
 lora:
  # Rank of the LoRA matrices (higher = more capacity but more parameters)
  # Typical values: 8, 16, 32, 64. Start with 32 for general fine-tuning.
  rank: 32
  # Alpha scaling factor (usually set equal to rank)
  # The effective scaling is alpha/rank, so alpha=rank means scaling of 1.0
  alpha: 32
  # Dropout probability for LoRA layers (0.0 = no dropout)
  # Can help with regularization if overfitting occurs
  dropout: 0.0
  # Which transformer modules to apply LoRA to
  # The LTX-2 transformer has separate attention and FFN blocks for video and audio:
  #
  # VIDEO MODULES:
  #   - attn1.to_k, attn1.to_q, attn1.to_v, attn1.to_out.0  (video self-attention)
  #   - attn2.to_k, attn2.to_q, attn2.to_v, attn2.to_out.0  (video cross-attention to text)
  #   - ff.net.0.proj, ff.net.2                             (video feed-forward)
  #
  # AUDIO MODULES:
  #   - audio_attn1.to_k, audio_attn1.to_q, audio_attn1.to_v, audio_attn1.to_out.0  (audio self-attention)
  #   - audio_attn2.to_k, audio_attn2.to_q, audio_attn2.to_v, audio_attn2.to_out.0  (audio cross-attention to text)
  #   - audio_ff.net.0.proj, audio_ff.net.2                                         (audio feed-forward)
  #
  # AUDIO-VIDEO CROSS-ATTENTION MODULES (for cross-modal interaction):
  #   - audio_to_video_attn.to_k, audio_to_video_attn.to_q, audio_to_video_attn.to_v, audio_to_video_attn.to_out.0
  #       (Q from video, K/V from audio - allows video to attend to audio features)
  #   - video_to_audio_attn.to_k, video_to_audio_attn.to_q, video_to_audio_attn.to_v, video_to_audio_attn.to_out.0
  #       (Q from audio, K/V from video - allows audio to attend to video features)
  #
  # Using short patterns like "to_k" matches ALL attention modules (video, audio, and cross-modal).
  # For audio-video training, this is the recommended approach.
  target_modules:
    # Attention layers (matches both video and audio branches)
    - "to_k"
    - "to_q"
    - "to_v"
    - "to_out.0"
    # Uncomment below to also train feed-forward layers (can increase the LoRA's capacity):
    # - "ff.net.0.proj"
    # - "ff.net.2"
    # - "audio_ff.net.0.proj"
    # - "audio_ff.net.2"
 # -----------------------------------------------------------------------------
 # Training Strategy Configuration
 # -----------------------------------------------------------------------------
 # Defines the training approach using the unified flexible strategy.
 # This configuration trains both video and audio generation from text prompts.
 training_strategy:
  # Strategy name: "flexible" for the unified conditioning framework
  # Supports all training modes (T2V, I2V, V2V, A2V, V2A, etc.) through
  # modality-specific configuration blocks.
  name: "flexible"
  # Video modality configuration
  # When is_generated is true, the model learns to generate (denoise) video
  video:
    # Whether the model generates video (true) or uses it as frozen conditioning (false)
    is_generated: true
    # Directory name (within preprocessed_data_root) containing video latents
    latents_dir: "latents"
  # Audio modality configuration
  # When is_generated is true, the model learns to generate (denoise) audio
  audio:
    # Whether the model generates audio (true) or uses it as frozen conditioning (false)
    is_generated: true
    # Directory name (within preprocessed_data_root) containing audio latents
    latents_dir: "audio_latents"
 # -----------------------------------------------------------------------------
 # Optimization Configuration
 # -----------------------------------------------------------------------------
 # Controls the training optimization parameters.
 optimization:
  # Learning rate for the optimizer
  # Typical range for LoRA: 1e-5 to 1e-4
  learning_rate: 1e-4
  # Total number of training steps
  steps: 2000
  # Batch size per GPU
  # Reduce if running out of memory
  batch_size: 1
  # Number of gradient accumulation steps
  # Effective batch size = batch_size * gradient_accumulation_steps * num_gpus
  gradient_accumulation_steps: 1
  # Maximum gradient norm for clipping (helps training stability)
  max_grad_norm: 1.0
  # Optimizer type: "adamw" (standard) or "adamw8bit" (memory-efficient)
  optimizer_type: "adamw"
  # Learning rate scheduler type
  # Options: "constant", "linear", "cosine", "cosine_with_restarts", "polynomial"
  scheduler_type: "linear"
  # Additional scheduler parameters (depends on scheduler_type)
  scheduler_params: { }
  # Enable gradient checkpointing to reduce memory usage
  # Recommended for training with limited GPU memory
  enable_gradient_checkpointing: true
 # -----------------------------------------------------------------------------
 # Acceleration Configuration
 # -----------------------------------------------------------------------------
 # Hardware acceleration and memory optimization settings.
 acceleration:
  # Mixed precision training mode
  # Options: "no" (fp32), "fp16" (half precision), "bf16" (bfloat16, recommended)
  mixed_precision_mode: "bf16"
  # Model quantization for reduced memory usage
  # Options: null (none), "int8-quanto", "int4-quanto", "int2-quanto", "fp8-quanto", "fp8uz-quanto"
  quantization: null
  # Load text encoder in 8-bit precision to save memory
  # Useful when GPU memory is limited
  load_text_encoder_in_8bit: false
  # Offload optimizer state to CPU during validation video sampling and restore it after.
  # Frees VRAM for the VAE decoder when optimizer state is large (full fine-tune, high-rank
  # LoRA). No effect under FSDP (sharded state).
  offload_optimizer_during_validation: false
 # -----------------------------------------------------------------------------
 # Data Configuration
 # -----------------------------------------------------------------------------
 # Specifies the training data location and loading parameters.
 data:
  # Root directory containing preprocessed training data
  # Should contain: latents/, conditions/, and audio_latents/
  preprocessed_data_root: "/path/to/preprocessed/data"
  # Number of worker processes for data loading
  # Used for parallel data loading to speed up data loading
  num_dataloader_workers: 2
 # -----------------------------------------------------------------------------
 # Validation Configuration
 # -----------------------------------------------------------------------------
 # Controls validation sampling during training.
 # NOTE: Validation sampling use simplified inference pipelines and prioritizes speed over
 # maximum quality. For production-quality inference, use `packages/ltx-pipelines`.
 validation:
  # Validation samples — each sample describes a self-contained generation request.
  # Use 'conditions' to add conditioning (first_frame, prefix, suffix, reference, video_to_audio, etc.)
  # See docs/configuration-reference.md#validation-condition-types for the full list of condition types.
  samples:
    - prompt: >-
        A woman with long brown hair sits at a wooden desk in a cozy home office, typing on a
        laptop while occasionally glancing at notes beside her. Soft natural light streams through
        a large window, casting warm shadows across the room. She pauses to take a sip from a
        ceramic mug, then continues working with focused concentration. The audio captures the
        gentle clicking of keyboard keys, the soft rustle of papers, and ambient room tone with
        occasional distant bird chirps from outside.
    - prompt: >-
        A chef in a white uniform stands in a professional kitchen, carefully plating a gourmet
        dish with precise movements. Steam rises from freshly cooked vegetables as he arranges
        them with tweezers. The stainless steel surfaces gleam under bright overhead lights, and
        various pots simmer on the stove behind him. The audio features the sizzling of pans,
        the clinking of utensils against plates, and the ambient hum of kitchen ventilation.
  # Negative prompt to avoid unwanted artifacts
  negative_prompt: "worst quality, inconsistent motion, blurry, jittery, distorted"
  # Output video dimensions [width, height, frames]
  # Width and height must be divisible by 32
  # Frames must satisfy: frames % 8 == 1 (e.g., 1, 9, 17, 25, 33, 41, 49, 57, 65, 73, 81, 89, ...)
  video_dims: [ 576, 576, 89 ]
  # Frame rate for generated videos
  frame_rate: 25.0
  # Random seed for reproducible validation outputs
  seed: 42
  # Number of denoising steps for validation inference
  # Higher values = better quality but slower generation
  inference_steps: 30
  # Generate validation videos every N training steps
  # Set to null to disable validation during training
  interval: 100
  # Classifier-free guidance scale
  # Higher values = stronger adherence to prompt but may introduce artifacts
  guidance_scale: 4.0
  # STG (Spatio-Temporal Guidance) parameters for improved video quality
  # STG is combined with CFG for better temporal coherence
  stg_scale: 1.0  # Recommended: 1.0 (0.0 disables STG)
  stg_blocks: [29]  # Recommended: single block 29
  stg_mode: "stg_av"  # "stg_av" perturbs both audio and video, "stg_v" video only
  # Whether to generate audio in validation samples
  # Independent of training_strategy.audio.is_generated - you can generate audio
  # in validation even when not training the audio branch
  generate_audio: true
  # Skip validation at the beginning of training (step 0)
  skip_initial_validation: false
 # -----------------------------------------------------------------------------
 # Checkpoint Configuration
 # -----------------------------------------------------------------------------
 # Controls model checkpoint saving during training.
 checkpoints:
  # Save a checkpoint every N steps
  # Set to null to disable intermediate checkpoints
  interval: 250
  # Number of most recent checkpoints to keep
  # Set to -1 to keep all checkpoints
  keep_last_n: -1
  # Precision to use when saving checkpoint weights
  # Options: "bfloat16" (default, smaller files) or "float32" (full precision)
  precision: "bfloat16"
 # -----------------------------------------------------------------------------
 # Flow Matching Configuration
 # -----------------------------------------------------------------------------
 # Parameters for the flow matching training objective.
 flow_matching:
  # Timestep sampling mode
  # "shifted_logit_normal" is recommended for LTX-2 models
  timestep_sampling_mode: "shifted_logit_normal"
  # Additional parameters for timestep sampling
  timestep_sampling_params: { }
 # -----------------------------------------------------------------------------
 # Hugging Face Hub Configuration
 # -----------------------------------------------------------------------------
 # Settings for uploading trained models to the Hugging Face Hub.
 hub:
  # Whether to push the trained model to the Hub
  push_to_hub: false
  # Repository ID on Hugging Face Hub (e.g., "username/my-lora-model")
  # Required if push_to_hub is true
  hub_model_id: null
 # -----------------------------------------------------------------------------
 # Weights & Biases Configuration
 # -----------------------------------------------------------------------------
 # Settings for experiment tracking with W&B.
 wandb:
  # Enable W&B logging
  enabled: false
  # W&B project name
  project: "ltx-2-trainer"
  # W&B username or team (null uses default account)
  entity: null
  # Tags to help organize runs
  tags: [ "ltx2", "lora", "t2v" ]
  # Log validation media (video/audio) to W&B
  log_validation_videos: true
 # -----------------------------------------------------------------------------
 # General Configuration
 # -----------------------------------------------------------------------------
 # Global settings for the training run.
 # Random seed for reproducibility
 seed: 42
 # Directory to save outputs (checkpoints, validation videos, logs)
 output_dir: "outputs/t2v_lora"
@@ -1,339 +0,0 @@
 # =============================================================================
 # LTX-2 Text-to-Video LoRA Training Configuration (Low VRAM)
 # =============================================================================
 #
 # This is a memory-optimized variant of the standard text-to-video LoRA config.
 # It uses 8-bit optimizer, int8 quantization, and reduced LoRA rank to minimize
 # GPU memory usage while maintaining good training quality.
 #
 # Memory optimizations applied:
 #   - 8-bit AdamW optimizer (reduces optimizer state memory by ~75%)
 #   - INT8 model quantization (reduces model memory by ~50%)
 #   - Lower LoRA rank (16 vs 32, reduces trainable parameters)
 #   - Gradient checkpointing enabled
 #
 # Recommended for GPUs with 32GB VRAM (e.g., RTX 5090).
 #
 # Use this configuration when you want to:
 #   - Fine-tune LTX-2 on your own video dataset with limited GPU memory
 #   - Train joint audio-video generation from text prompts
 #   - Create custom video generation styles or audiovisual concepts
 #
 # Dataset structure:
 #   preprocessed_data_root/
 #   ├── latents/        # Video latents (VAE-encoded videos)
 #   ├── conditions/     # Text embeddings for each video
 #   └── audio_latents/  # Audio latents (VAE-encoded audio)
 #
 # =============================================================================
 # -----------------------------------------------------------------------------
 # Model Configuration
 # -----------------------------------------------------------------------------
 # Specifies the base model to fine-tune and the training mode.
 model:
  # Path to the LTX-2 model checkpoint (.safetensors file)
  # This should be a local path to your downloaded model
  model_path: "path/to/ltx-2-model.safetensors"
  # Path to the text encoder model directory
  # For LTX-2, this is typically the Gemma-based text encoder
  text_encoder_path: "path/to/gemma-text-encoder"
  # Training mode: "lora" for efficient adapter training, "full" for full fine-tuning
  # LoRA is recommended for most use cases (faster, less memory, prevents overfitting)
  training_mode: "lora"
  # Optional: Path to resume training from a checkpoint
  # Can be a checkpoint file (.safetensors) or directory (uses latest checkpoint)
  load_checkpoint: null
 # -----------------------------------------------------------------------------
 # LoRA Configuration
 # -----------------------------------------------------------------------------
 # Controls the Low-Rank Adaptation parameters for efficient fine-tuning.
 # Using a lower rank (16) to reduce trainable parameters and memory usage.
 # This still provides good capacity for many fine-tuning tasks.
 lora:
  # Rank of the LoRA matrices (higher = more capacity but more parameters)
  # Typical values: 8, 16, 32, 64. Using 16 for low VRAM configuration.
  rank: 16
  # Alpha scaling factor (usually set equal to rank)
  # The effective scaling is alpha/rank, so alpha=rank means scaling of 1.0
  alpha: 16
  # Dropout probability for LoRA layers (0.0 = no dropout)
  # Can help with regularization if overfitting occurs
  dropout: 0.0
  # Which transformer modules to apply LoRA to
  # The LTX-2 transformer has separate attention and FFN blocks for video and audio:
  #
  # VIDEO MODULES:
  #   - attn1.to_k, attn1.to_q, attn1.to_v, attn1.to_out.0  (video self-attention)
  #   - attn2.to_k, attn2.to_q, attn2.to_v, attn2.to_out.0  (video cross-attention to text)
  #   - ff.net.0.proj, ff.net.2                             (video feed-forward)
  #
  # AUDIO MODULES:
  #   - audio_attn1.to_k, audio_attn1.to_q, audio_attn1.to_v, audio_attn1.to_out.0  (audio self-attention)
  #   - audio_attn2.to_k, audio_attn2.to_q, audio_attn2.to_v, audio_attn2.to_out.0  (audio cross-attention to text)
  #   - audio_ff.net.0.proj, audio_ff.net.2                                         (audio feed-forward)
  #
  # AUDIO-VIDEO CROSS-ATTENTION MODULES (for cross-modal interaction):
  #   - audio_to_video_attn.to_k, audio_to_video_attn.to_q, audio_to_video_attn.to_v, audio_to_video_attn.to_out.0
  #       (Q from video, K/V from audio - allows video to attend to audio features)
  #   - video_to_audio_attn.to_k, video_to_audio_attn.to_q, video_to_audio_attn.to_v, video_to_audio_attn.to_out.0
  #       (Q from audio, K/V from video - allows audio to attend to video features)
  #
  # Using short patterns like "to_k" matches ALL attention modules (video, audio, and cross-modal).
  # For audio-video training, this is the recommended approach.
  target_modules:
    # Attention layers (matches both video and audio branches)
    - "to_k"
    - "to_q"
    - "to_v"
    - "to_out.0"
    # Uncomment below to also train feed-forward layers (can increase the LoRA's capacity):
    # - "ff.net.0.proj"
    # - "ff.net.2"
    # - "audio_ff.net.0.proj"
    # - "audio_ff.net.2"
 # -----------------------------------------------------------------------------
 # Training Strategy Configuration
 # -----------------------------------------------------------------------------
 # Defines the training approach using the unified flexible strategy.
 # This configuration trains both video and audio generation from text prompts.
 training_strategy:
  # Strategy name: "flexible" for the unified conditioning framework
  # Supports all training modes (T2V, I2V, V2V, A2V, V2A, etc.) through
  # modality-specific configuration blocks.
  name: "flexible"
  # Video modality configuration
  # When is_generated is true, the model learns to generate (denoise) video
  video:
    # Whether the model generates video (true) or uses it as frozen conditioning (false)
    is_generated: true
    # Directory name (within preprocessed_data_root) containing video latents
    latents_dir: "latents"
  # Audio modality configuration
  # When is_generated is true, the model learns to generate (denoise) audio
  audio:
    # Whether the model generates audio (true) or uses it as frozen conditioning (false)
    is_generated: true
    # Directory name (within preprocessed_data_root) containing audio latents
    latents_dir: "audio_latents"
 # -----------------------------------------------------------------------------
 # Optimization Configuration
 # -----------------------------------------------------------------------------
 # Controls the training optimization parameters.
 optimization:
  # Learning rate for the optimizer
  # Typical range for LoRA: 1e-5 to 1e-4
  learning_rate: 1e-4
  # Total number of training steps
  steps: 2000
  # Batch size per GPU
  # Reduce if running out of memory
  batch_size: 1
  # Number of gradient accumulation steps
  # Effective batch size = batch_size * gradient_accumulation_steps * num_gpus
  gradient_accumulation_steps: 1
  # Maximum gradient norm for clipping (helps training stability)
  max_grad_norm: 1.0
  # Optimizer type: "adamw" (standard) or "adamw8bit" (memory-efficient)
  # Using 8-bit AdamW to reduce optimizer state memory by ~75%
  optimizer_type: "adamw8bit"
  # Learning rate scheduler type
  # Options: "constant", "linear", "cosine", "cosine_with_restarts", "polynomial"
  scheduler_type: "linear"
  # Additional scheduler parameters (depends on scheduler_type)
  scheduler_params: { }
  # Enable gradient checkpointing to reduce memory usage
  # Recommended for training with limited GPU memory
  enable_gradient_checkpointing: true
 # -----------------------------------------------------------------------------
 # Acceleration Configuration
 # -----------------------------------------------------------------------------
 # Hardware acceleration and memory optimization settings.
 acceleration:
  # Mixed precision training mode
  # Options: "no" (fp32), "fp16" (half precision), "bf16" (bfloat16, recommended)
  mixed_precision_mode: "bf16"
  # Model quantization for reduced memory usage
  # Options: null (none), "int8-quanto", "int4-quanto", "int2-quanto", "fp8-quanto", "fp8uz-quanto"
  # Using INT8 quantization to reduce base model memory consumption by ~50%
  quantization: "int8-quanto"
  # Load text encoder in 8-bit precision to save memory
  # Useful when GPU memory is limited
  load_text_encoder_in_8bit: true
  # Offload optimizer state to CPU during validation video sampling and restore it after.
  # Frees VRAM for the VAE decoder when optimizer state is large (full fine-tune, high-rank
  # LoRA). No effect under FSDP (sharded state).
  offload_optimizer_during_validation: true
 # -----------------------------------------------------------------------------
 # Data Configuration
 # -----------------------------------------------------------------------------
 # Specifies the training data location and loading parameters.
 data:
  # Root directory containing preprocessed training data
  # Should contain: latents/, conditions/, and audio_latents/
  preprocessed_data_root: "/path/to/preprocessed/data"
  # Number of worker processes for data loading
  # Used for parallel data loading to speed up data loading
  num_dataloader_workers: 2
 # -----------------------------------------------------------------------------
 # Validation Configuration
 # -----------------------------------------------------------------------------
 # Controls validation sampling during training.
 # NOTE: Validation sampling use simplified inference pipelines and prioritizes speed over
 # maximum quality. For production-quality inference, use `packages/ltx-pipelines`.
 validation:
  # Validation samples — each sample describes a self-contained generation request.
  # Use 'conditions' to add conditioning (first_frame, prefix, suffix, reference, video_to_audio, etc.)
  # See docs/configuration-reference.md#validation-condition-types for the full list of condition types.
  samples:
    - prompt: >-
        A woman with long brown hair sits at a wooden desk in a cozy home office, typing on a
        laptop while occasionally glancing at notes beside her. Soft natural light streams through
        a large window, casting warm shadows across the room. She pauses to take a sip from a
        ceramic mug, then continues working with focused concentration. The audio captures the
        gentle clicking of keyboard keys, the soft rustle of papers, and ambient room tone with
        occasional distant bird chirps from outside.
    - prompt: >-
        A chef in a white uniform stands in a professional kitchen, carefully plating a gourmet
        dish with precise movements. Steam rises from freshly cooked vegetables as he arranges
        them with tweezers. The stainless steel surfaces gleam under bright overhead lights, and
        various pots simmer on the stove behind him. The audio features the sizzling of pans,
        the clinking of utensils against plates, and the ambient hum of kitchen ventilation.
  # Negative prompt to avoid unwanted artifacts
  negative_prompt: "worst quality, inconsistent motion, blurry, jittery, distorted"
  # Output video dimensions [width, height, frames]
  # Width and height must be divisible by 32
  # Frames must satisfy: frames % 8 == 1 (e.g., 1, 9, 17, 25, 33, 41, 49, 57, 65, 73, 81, 89, ...)
  video_dims: [ 576, 576, 49 ]
  # Frame rate for generated videos
  frame_rate: 25.0
  # Random seed for reproducible validation outputs
  seed: 42
  # Number of denoising steps for validation inference
  # Higher values = better quality but slower generation
  inference_steps: 30
  # Generate validation videos every N training steps
  # Set to null to disable validation during training
  interval: 100
  # Classifier-free guidance scale
  # Higher values = stronger adherence to prompt but may introduce artifacts
  guidance_scale: 4.0
  # STG (Spatio-Temporal Guidance) parameters for improved video quality
  # STG is combined with CFG for better temporal coherence
  stg_scale: 1.0  # Recommended: 1.0 (0.0 disables STG)
  stg_blocks: [ 29 ]  # Recommended: single block 29
  stg_mode: "stg_av"  # "stg_av" perturbs both audio and video, "stg_v" video only
  # Whether to generate audio in validation samples
  # Independent of training_strategy audio modality settings — you can generate audio
  # in validation even when not training the audio branch
  generate_audio: true
  # Skip validation at the beginning of training (step 0)
  skip_initial_validation: false
 # -----------------------------------------------------------------------------
 # Checkpoint Configuration
 # -----------------------------------------------------------------------------
 # Controls model checkpoint saving during training.
 checkpoints:
  # Save a checkpoint every N steps
  # Set to null to disable intermediate checkpoints
  interval: 250
  # Number of most recent checkpoints to keep
  # Set to -1 to keep all checkpoints
  keep_last_n: -1
  # Precision to use when saving checkpoint weights
  # Options: "bfloat16" (default, smaller files) or "float32" (full precision)
  precision: "bfloat16"
 # -----------------------------------------------------------------------------
 # Flow Matching Configuration
 # -----------------------------------------------------------------------------
 # Parameters for the flow matching training objective.
 flow_matching:
  # Timestep sampling mode
  # "shifted_logit_normal" is recommended for LTX-2 models
  timestep_sampling_mode: "shifted_logit_normal"
  # Additional parameters for timestep sampling
  timestep_sampling_params: { }
 # -----------------------------------------------------------------------------
 # Hugging Face Hub Configuration
 # -----------------------------------------------------------------------------
 # Settings for uploading trained models to the Hugging Face Hub.
 hub:
  # Whether to push the trained model to the Hub
  push_to_hub: false
  # Repository ID on Hugging Face Hub (e.g., "username/my-lora-model")
  # Required if push_to_hub is true
  hub_model_id: null
 # -----------------------------------------------------------------------------
 # Weights & Biases Configuration
 # -----------------------------------------------------------------------------
 # Settings for experiment tracking with W&B.
 wandb:
  # Enable W&B logging
  enabled: false
  # W&B project name
  project: "ltx-2-trainer"
  # W&B username or team (null uses default account)
  entity: null
  # Tags to help organize runs
  tags: [ "ltx2", "lora", "t2v", "low-vram" ]
  # Log validation media (video/audio) to W&B
  log_validation_videos: true
 # -----------------------------------------------------------------------------
 # General Configuration
 # -----------------------------------------------------------------------------
 # Global settings for the training run.
 # Random seed for reproducibility
 seed: 42
 # Directory to save outputs (checkpoints, validation videos, logs)
 output_dir: "outputs/t2v_lora_low_vram"
@@ -1,349 +0,0 @@
 # =============================================================================
 # LTX-2 Video-to-Audio (Foley) LoRA Training Configuration
 # =============================================================================
 #
 # This configuration is for training LoRA adapters on the LTX-2 model for
 # video-to-audio (Foley) generation. The model learns to generate audio
 # conditioned on a frozen video signal via the transformer's built-in
 # cross-modal attention.
 #
 # In this mode, video is provided as a frozen (clean, no noise, no loss)
 # conditioning signal. The audio modality is the only generated output.
 # Video influences audio generation through the transformer's video-to-audio
 # cross-attention mechanism.
 #
 # Use this configuration when you want to:
 #   - Generate sound effects (Foley) for existing videos
 #   - Train audio generation conditioned on visual content
 #   - Create models that produce audio matching video content
 #
 # Dataset structure:
 #   preprocessed_data_root/
 #   ├── latents/        # Video latents (frozen conditioning input)
 #   ├── conditions/     # Text embeddings for each video
 #   └── audio_latents/  # Audio latents (VAE-encoded audio, generated output)
 #
 # =============================================================================
 # -----------------------------------------------------------------------------
 # Model Configuration
 # -----------------------------------------------------------------------------
 # Specifies the base model to fine-tune and the training mode.
 model:
  # Path to the LTX-2 model checkpoint (.safetensors file)
  # This should be a local path to your downloaded model
  model_path: "path/to/ltx-2-model.safetensors"
  # Path to the text encoder model directory
  # For LTX-2, this is typically the Gemma-based text encoder
  text_encoder_path: "path/to/gemma-text-encoder"
  # Training mode: "lora" for efficient adapter training, "full" for full fine-tuning
  # LoRA is recommended for most use cases (faster, less memory, prevents overfitting)
  training_mode: "lora"
  # Optional: Path to resume training from a checkpoint
  # Can be a checkpoint file (.safetensors) or directory (uses latest checkpoint)
  load_checkpoint: null
 # -----------------------------------------------------------------------------
 # LoRA Configuration
 # -----------------------------------------------------------------------------
 # Controls the Low-Rank Adaptation parameters for efficient fine-tuning.
 lora:
  # Rank of the LoRA matrices (higher = more capacity but more parameters)
  # Typical values: 8, 16, 32, 64. Start with 32 for general fine-tuning.
  rank: 32
  # Alpha scaling factor (usually set equal to rank)
  # The effective scaling is alpha/rank, so alpha=rank means scaling of 1.0
  alpha: 32
  # Dropout probability for LoRA layers (0.0 = no dropout)
  # Can help with regularization if overfitting occurs
  dropout: 0.0
  # Which transformer modules to apply LoRA to
  # The LTX-2 transformer has separate attention and FFN blocks for video and audio:
  #
  # VIDEO MODULES:
  #   - attn1.to_k, attn1.to_q, attn1.to_v, attn1.to_out.0  (video self-attention)
  #   - attn2.to_k, attn2.to_q, attn2.to_v, attn2.to_out.0  (video cross-attention to text)
  #   - ff.net.0.proj, ff.net.2                             (video feed-forward)
  #
  # AUDIO MODULES:
  #   - audio_attn1.to_k, audio_attn1.to_q, audio_attn1.to_v, audio_attn1.to_out.0  (audio self-attention)
  #   - audio_attn2.to_k, audio_attn2.to_q, audio_attn2.to_v, audio_attn2.to_out.0  (audio cross-attention to text)
  #   - audio_ff.net.0.proj, audio_ff.net.2                                         (audio feed-forward)
  #
  # AUDIO-VIDEO CROSS-ATTENTION MODULES (for cross-modal interaction):
  #   - audio_to_video_attn.to_k, audio_to_video_attn.to_q, audio_to_video_attn.to_v, audio_to_video_attn.to_out.0
  #       (Q from video, K/V from audio - allows video to attend to audio features)
  #   - video_to_audio_attn.to_k, video_to_audio_attn.to_q, video_to_audio_attn.to_v, video_to_audio_attn.to_out.0
  #       (Q from audio, K/V from video - allows audio to attend to video features)
  #
  # For video-to-audio training, we target audio modules and the cross-modal
  # attention that allows audio to attend to video features.
  target_modules:
    # Audio self-attention
    - "audio_attn1.to_k"
    - "audio_attn1.to_q"
    - "audio_attn1.to_v"
    - "audio_attn1.to_out.0"
    # Audio cross-attention to text
    - "audio_attn2.to_k"
    - "audio_attn2.to_q"
    - "audio_attn2.to_v"
    - "audio_attn2.to_out.0"
    # Audio feed-forward
    - "audio_ff.net.0.proj"
    - "audio_ff.net.2"
    # Cross-modal attention: allows audio to attend to video features
    - "video_to_audio_attn.to_k"
    - "video_to_audio_attn.to_q"
    - "video_to_audio_attn.to_v"
    - "video_to_audio_attn.to_out.0"
 # -----------------------------------------------------------------------------
 # Training Strategy Configuration
 # -----------------------------------------------------------------------------
 # Defines the video-to-audio (Foley) training approach using the unified
 # flexible strategy. Video is frozen (no noise, sigma=0, excluded from loss)
 # and conditions audio generation via the transformer's cross-modal attention.
 training_strategy:
  # Strategy name: "flexible" for the unified conditioning framework
  # Supports all training modes (T2V, I2V, V2V, A2V, V2A, etc.) through
  # modality-specific configuration blocks.
  name: "flexible"
  # Video modality configuration
  # Video is frozen — it acts as conditioning for audio generation
  # Frozen modalities get sigma=0, timestep=0, no noise, and no loss
  video:
    # Whether the model generates video (true) or uses it as frozen conditioning (false)
    # When false, video is passed through the transformer clean and influences
    # audio via cross-modal attention
    is_generated: false
    # Directory name (within preprocessed_data_root) containing video latents
    latents_dir: "latents"
  # Audio modality configuration
  # Audio is the generated (denoised) output
  audio:
    # Whether the model generates audio (true) or uses it as frozen conditioning (false)
    is_generated: true
    # Directory name (within preprocessed_data_root) containing audio latents
    latents_dir: "audio_latents"
 # -----------------------------------------------------------------------------
 # Optimization Configuration
 # -----------------------------------------------------------------------------
 # Controls the training optimization parameters.
 optimization:
  # Learning rate for the optimizer
  # Typical range for LoRA: 1e-5 to 1e-4
  learning_rate: 1e-4
  # Total number of training steps
  steps: 2000
  # Batch size per GPU
  # Reduce if running out of memory
  batch_size: 1
  # Number of gradient accumulation steps
  # Effective batch size = batch_size * gradient_accumulation_steps * num_gpus
  gradient_accumulation_steps: 1
  # Maximum gradient norm for clipping (helps training stability)
  max_grad_norm: 1.0
  # Optimizer type: "adamw" (standard) or "adamw8bit" (memory-efficient)
  optimizer_type: "adamw"
  # Learning rate scheduler type
  # Options: "constant", "linear", "cosine", "cosine_with_restarts", "polynomial"
  scheduler_type: "linear"
  # Additional scheduler parameters (depends on scheduler_type)
  scheduler_params: { }
  # Enable gradient checkpointing to reduce memory usage
  # Recommended for training with limited GPU memory
  enable_gradient_checkpointing: true
 # -----------------------------------------------------------------------------
 # Acceleration Configuration
 # -----------------------------------------------------------------------------
 # Hardware acceleration and memory optimization settings.
 acceleration:
  # Mixed precision training mode
  # Options: "no" (fp32), "fp16" (half precision), "bf16" (bfloat16, recommended)
  mixed_precision_mode: "bf16"
  # Model quantization for reduced memory usage
  # Options: null (none), "int8-quanto", "int4-quanto", "int2-quanto", "fp8-quanto", "fp8uz-quanto"
  quantization: null
  # Load text encoder in 8-bit precision to save memory
  # Useful when GPU memory is limited
  load_text_encoder_in_8bit: false
  # Offload optimizer state to CPU during validation video sampling and restore it after.
  # Frees VRAM for the VAE decoder when optimizer state is large (full fine-tune, high-rank
  # LoRA). No effect under FSDP (sharded state).
  offload_optimizer_during_validation: false
 # -----------------------------------------------------------------------------
 # Data Configuration
 # -----------------------------------------------------------------------------
 # Specifies the training data location and loading parameters.
 data:
  # Root directory containing preprocessed training data
  # Should contain: latents/, audio_latents/, and conditions/
  preprocessed_data_root: "/path/to/preprocessed/data"
  # Number of worker processes for data loading
  # Used for parallel data loading to speed up data loading
  num_dataloader_workers: 2
 # -----------------------------------------------------------------------------
 # Validation Configuration
 # -----------------------------------------------------------------------------
 # Controls validation sampling during training.
 # NOTE: Validation sampling use simplified inference pipelines and prioritizes speed over
 # maximum quality. For production-quality inference, use `packages/ltx-pipelines`.
 validation:
  # Validation samples — each sample describes a self-contained generation request.
  # Use 'conditions' to add conditioning (first_frame, prefix, suffix, reference, video_to_audio, etc.)
  # See docs/configuration-reference.md#validation-condition-types for the full list of condition types.
  samples:
    - prompt: >-
        The sound of ocean waves crashing against rocky cliffs, with seagulls calling in the
        distance and wind whistling through coastal grass.
      conditions:
        - type: video_to_audio
          video: "/path/to/conditioning_video_1.mp4"
    - prompt: >-
        Footsteps echo in a marble hallway as a person walks steadily, with the distant hum of
        air conditioning and occasional door closing sounds.
      conditions:
        - type: video_to_audio
          video: "/path/to/conditioning_video_2.mp4"
  # Negative prompt to avoid unwanted artifacts
  negative_prompt: "worst quality, inconsistent motion, blurry, jittery, distorted"
  # Validation dimensions [width, height, frames]
  # Width/height resize the frozen video condition; frames and frame_rate set audio duration.
  # Frames must satisfy: frames % 8 == 1 (e.g., 1, 9, 17, 25, 33, 41, 49, 57, 65, 73, 81, 89, ...)
  video_dims: [ 576, 576, 89 ]
  # Frame rate for generated videos
  frame_rate: 25.0
  # Random seed for reproducible validation outputs
  seed: 42
  # Number of denoising steps for validation inference
  # Higher values = better quality but slower generation
  inference_steps: 30
  # Generate validation videos every N training steps
  # Set to null to disable validation during training
  interval: 100
  # Classifier-free guidance scale
  # Higher values = stronger adherence to prompt but may introduce artifacts
  guidance_scale: 4.0
  # STG (Spatio-Temporal Guidance) parameters for improved video quality
  # STG is combined with CFG for better temporal coherence
  stg_scale: 1.0  # Recommended: 1.0 (0.0 disables STG)
  stg_blocks: [29]  # Recommended: single block 29
  stg_mode: "stg_av"  # "stg_av" perturbs both audio and video, "stg_v" video only
  # Whether to generate audio in validation samples
  # Independent of training_strategy.audio.is_generated - you can generate audio
  # in validation even when not training the audio branch
  generate_audio: true
  # Whether to generate video in validation samples
  # Disabled for V2A since video is frozen conditioning, not generated
  generate_video: false
  # Skip validation at the beginning of training (step 0)
  skip_initial_validation: false
 # -----------------------------------------------------------------------------
 # Checkpoint Configuration
 # -----------------------------------------------------------------------------
 # Controls model checkpoint saving during training.
 checkpoints:
  # Save a checkpoint every N steps
  # Set to null to disable intermediate checkpoints
  interval: 250
  # Number of most recent checkpoints to keep
  # Set to -1 to keep all checkpoints
  keep_last_n: -1
  # Precision to use when saving checkpoint weights
  # Options: "bfloat16" (default, smaller files) or "float32" (full precision)
  precision: "bfloat16"
 # -----------------------------------------------------------------------------
 # Flow Matching Configuration
 # -----------------------------------------------------------------------------
 # Parameters for the flow matching training objective.
 flow_matching:
  # Timestep sampling mode
  # "shifted_logit_normal" is recommended for LTX-2 models
  timestep_sampling_mode: "shifted_logit_normal"
  # Additional parameters for timestep sampling
  timestep_sampling_params: { }
 # -----------------------------------------------------------------------------
 # Hugging Face Hub Configuration
 # -----------------------------------------------------------------------------
 # Settings for uploading trained models to the Hugging Face Hub.
 hub:
  # Whether to push the trained model to the Hub
  push_to_hub: false
  # Repository ID on Hugging Face Hub (e.g., "username/my-lora-model")
  # Required if push_to_hub is true
  hub_model_id: null
 # -----------------------------------------------------------------------------
 # Weights & Biases Configuration
 # -----------------------------------------------------------------------------
 # Settings for experiment tracking with W&B.
 wandb:
  # Enable W&B logging
  enabled: false
  # W&B project name
  project: "ltx-2-trainer"
  # W&B username or team (null uses default account)
  entity: null
  # Tags to help organize runs
  tags: [ "ltx2", "lora", "v2a", "foley" ]
  # Log validation media (video/audio) to W&B
  log_validation_videos: true
 # -----------------------------------------------------------------------------
 # General Configuration
 # -----------------------------------------------------------------------------
 # Global settings for the training run.
 # Random seed for reproducibility
 seed: 42
 # Directory to save outputs (checkpoints, validation videos, logs)
 output_dir: "outputs/v2a_lora"
@@ -1,359 +0,0 @@
 # =============================================================================
 # LTX-2 Video-to-Video (IC-LoRA) Training Configuration
 # =============================================================================
 #
 # This configuration is for training In-Context LoRA (IC-LoRA) adapters that
 # enable video-to-video transformations. IC-LoRA learns to apply visual
 # transformations (e.g., depth-to-video, pose control, style transfer, etc.)
 # by conditioning on reference videos.
 #
 # Key differences from text-to-video LoRA:
 #   - Uses reference videos as conditioning input alongside text prompts
 #   - Requires preprocessed reference latents in addition to target latents
 #   - Validation requires reference videos to demonstrate the transformation
 #
 # Dataset structure for IC-LoRA training:
 #   preprocessed_data_root/
 #   ├── latents/           # Target video latents (what the model learns to generate)
 #   ├── conditions/        # Text embeddings for each video
 #   └── reference_latents/ # Reference video latents (conditioning input)
 #
 # Dataset metadata columns: video, reference_video, caption
 #
 # =============================================================================
 # -----------------------------------------------------------------------------
 # Model Configuration
 # -----------------------------------------------------------------------------
 # Specifies the base model to fine-tune and the training mode.
 model:
  # Path to the LTX-2 model checkpoint (.safetensors file)
  # This should be a local path to your downloaded model
  model_path: "path/to/ltx-2-model.safetensors"
  # Path to the text encoder model directory
  # For LTX-2, this is typically the Gemma-based text encoder
  text_encoder_path: "path/to/gemma-text-encoder"
  # Training mode: "lora" for efficient adapter training, "full" for full fine-tuning
  # IC-LoRA reference conditioning is intended for LoRA adapter training.
  training_mode: "lora"
  # Optional: Path to resume training from a checkpoint
  # Can be a checkpoint file (.safetensors) or directory (uses latest checkpoint)
  load_checkpoint: null
 # -----------------------------------------------------------------------------
 # LoRA Configuration
 # -----------------------------------------------------------------------------
 # Controls the Low-Rank Adaptation parameters for efficient fine-tuning.
 lora:
  # Rank of the LoRA matrices (higher = more capacity but more parameters)
  # Typical values: 8, 16, 32, 64. Start with 16-32 for IC-LoRA.
  rank: 32
  # Alpha scaling factor (usually set equal to rank)
  # The effective scaling is alpha/rank, so alpha=rank means scaling of 1.0
  alpha: 32
  # Dropout probability for LoRA layers (0.0 = no dropout)
  # Can help with regularization if overfitting occurs
  dropout: 0.0
  # Which transformer modules to apply LoRA to
  # The LTX-2 transformer has separate attention and FFN blocks for video and audio:
  #
  # VIDEO MODULES:
  #   - attn1.to_k, attn1.to_q, attn1.to_v, attn1.to_out.0  (video self-attention)
  #   - attn2.to_k, attn2.to_q, attn2.to_v, attn2.to_out.0  (video cross-attention to text)
  #   - ff.net.0.proj, ff.net.2                             (video feed-forward)
  #
  # AUDIO MODULES (not used for video-only IC-LoRA):
  #   - audio_attn1.to_k, audio_attn1.to_q, audio_attn1.to_v, audio_attn1.to_out.0  (audio self-attention)
  #   - audio_attn2.to_k, audio_attn2.to_q, audio_attn2.to_v, audio_attn2.to_out.0  (audio cross-attention to text)
  #   - audio_ff.net.0.proj, audio_ff.net.2                                         (audio feed-forward)
  #
  # AUDIO-VIDEO CROSS-ATTENTION MODULES (for cross-modal interaction, not used for video-only IC-LoRA):
  #   - audio_to_video_attn.to_k, audio_to_video_attn.to_q, audio_to_video_attn.to_v, audio_to_video_attn.to_out.0
  #       (Q from video, K/V from audio - allows video to attend to audio features)
  #   - video_to_audio_attn.to_k, video_to_audio_attn.to_q, video_to_audio_attn.to_v, video_to_audio_attn.to_out.0
  #       (Q from audio, K/V from video - allows audio to attend to video features)
  #
  # For IC-LoRA (video-only), we explicitly target video modules.
  # Including FFN layers often improves transformation quality.
  target_modules:
    # Video self-attention
    - "attn1.to_k"
    - "attn1.to_q"
    - "attn1.to_v"
    - "attn1.to_out.0"
    # Video cross-attention
    - "attn2.to_k"
    - "attn2.to_q"
    - "attn2.to_v"
    - "attn2.to_out.0"
    # Video feed-forward (often improves transformation quality)
    - "ff.net.0.proj"
    - "ff.net.2"
 # -----------------------------------------------------------------------------
 # Training Strategy Configuration
 # -----------------------------------------------------------------------------
 # Defines the video-to-video (IC-LoRA) training approach using the unified
 # flexible strategy. Reference conditioning concatenates pre-encoded reference
 # video latents to the target sequence. Reference tokens participate in
 # bidirectional self-attention but receive no noise and are excluded from loss.
 training_strategy:
  # Strategy name: "flexible" for the unified conditioning framework
  # Supports all training modes (T2V, I2V, V2V, A2V, V2A, etc.) through
  # modality-specific configuration blocks.
  name: "flexible"
  # Video modality configuration
  video:
    # Whether the model generates video (true) or uses it as frozen conditioning (false)
    is_generated: true
    # Directory name (within preprocessed_data_root) containing target video latents
    latents_dir: "latents"
    # Conditions applied to the video modality during training
    conditions:
      # Reference conditioning (IC-LoRA): concatenates pre-encoded reference video
      # latents to the target sequence. The model learns to transform the reference
      # into the target video based on the text prompt.
      - type: reference
        # Directory name (within preprocessed_data_root) containing reference video latents
        # These are the conditioning inputs that guide the transformation
        latents_dir: "reference_latents"
        # Probability of applying reference conditioning per training sample
        probability: 1.0
      # Optional first-frame conditioning to improve I2V capabilities
      # At low probability, this teaches the model to also accept first-frame input
      - type: first_frame
        probability: 0.2
 # -----------------------------------------------------------------------------
 # Optimization Configuration
 # -----------------------------------------------------------------------------
 # Controls the training optimization parameters.
 optimization:
  # Learning rate for the optimizer
  # Typical range for LoRA: 1e-5 to 1e-4
  learning_rate: 2e-4
  # Total number of training steps
  steps: 3000
  # Batch size per GPU
  # Reduce if running out of memory
  batch_size: 1
  # Number of gradient accumulation steps
  # Effective batch size = batch_size * gradient_accumulation_steps * num_gpus
  gradient_accumulation_steps: 1
  # Maximum gradient norm for clipping (helps training stability)
  max_grad_norm: 1.0
  # Optimizer type: "adamw" (standard) or "adamw8bit" (memory-efficient)
  optimizer_type: "adamw"
  # Learning rate scheduler type
  # Options: "constant", "linear", "cosine", "cosine_with_restarts", "polynomial"
  scheduler_type: "linear"
  # Additional scheduler parameters (depends on scheduler_type)
  scheduler_params: { }
  # Enable gradient checkpointing to reduce memory usage
  # Recommended for training with limited GPU memory
  enable_gradient_checkpointing: true
 # -----------------------------------------------------------------------------
 # Acceleration Configuration
 # -----------------------------------------------------------------------------
 # Hardware acceleration and memory optimization settings.
 acceleration:
  # Mixed precision training mode
  # Options: "no" (fp32), "fp16" (half precision), "bf16" (bfloat16, recommended)
  mixed_precision_mode: "bf16"
  # Model quantization for reduced memory usage
  # Options: null (none), "int8-quanto", "int4-quanto", "int2-quanto", "fp8-quanto", "fp8uz-quanto"
  quantization: null
  # Load text encoder in 8-bit precision to save memory
  # Useful when GPU memory is limited
  load_text_encoder_in_8bit: false
  # Offload optimizer state to CPU during validation video sampling and restore it after.
  # Frees VRAM for the VAE decoder when optimizer state is large (full fine-tune, high-rank
  # LoRA). No effect under FSDP (sharded state).
  offload_optimizer_during_validation: false
 # -----------------------------------------------------------------------------
 # Data Configuration
 # -----------------------------------------------------------------------------
 # Specifies the training data location and loading parameters.
 data:
  # Root directory containing preprocessed training data
  # Should contain: latents/, conditions/, and reference_latents/ subdirectories
  preprocessed_data_root: "/path/to/preprocessed/data"
  # Number of worker processes for data loading
  # Used for parallel data loading to speed up data loading
  num_dataloader_workers: 2
 # -----------------------------------------------------------------------------
 # Validation Configuration
 # -----------------------------------------------------------------------------
 # Controls validation sampling during training.
 # NOTE: Validation sampling use simplified inference pipelines and prioritizes speed over
 # maximum quality. For production-quality inference, use `packages/ltx-pipelines`.
 validation:
  # Validation samples — each sample describes a self-contained generation request.
  # For IC-LoRA, each sample includes a reference condition pointing to the conditioning video.
  samples:
    - prompt: >-
        A man in a casual blue jacket walks along a winding path through a lush green park on a
        bright sunny afternoon. Tall oak trees line the pathway, their leaves rustling gently in
        the breeze. Dappled sunlight creates shifting patterns on the ground as he strolls at a
        relaxed pace, occasionally looking up at the scenery around him. The audio captures
        footsteps on gravel, birds singing in the trees, distant children playing, and the soft
        whisper of wind through the foliage.
      conditions:
        - type: reference
          video: "/path/to/reference_video_1.mp4"
          # Set these to match --reference-downscale-factor / --reference-temporal-scale-factor
          # if reference latents were preprocessed at reduced spatial or temporal resolution.
          downscale_factor: 1
          temporal_scale_factor: 1
          include_in_output: true
    - prompt: >-
        A fluffy orange tabby cat sits perfectly still on a wooden windowsill, its green eyes
        intently tracking small birds hopping on a branch just outside the glass. The cat's ears
        twitch and rotate, following every movement. Warm afternoon light illuminates its fur,
        creating a soft golden glow. Behind the cat, a cozy living room with a bookshelf and
        houseplants is visible. The audio features gentle purring, occasional soft meows, muffled
        bird chirps through the window, and quiet ambient room sounds.
      conditions:
        - type: reference
          video: "/path/to/reference_video_2.mp4"
          # Set these to match --reference-downscale-factor / --reference-temporal-scale-factor
          # if reference latents were preprocessed at reduced spatial or temporal resolution.
          downscale_factor: 1
          temporal_scale_factor: 1
          include_in_output: true
  # Negative prompt to avoid unwanted artifacts
  negative_prompt: "worst quality, inconsistent motion, blurry, jittery, distorted"
  # Output video dimensions [width, height, frames]
  # Width and height must be divisible by 32
  # Frames must satisfy: frames % 8 == 1 (e.g., 1, 9, 17, 25, 33, 41, 49, 57, 65, 73, 81, 89, ...)
  video_dims: [ 512, 512, 81 ]
  # Frame rate for generated videos
  frame_rate: 25.0
  # Random seed for reproducible validation outputs
  seed: 42
  # Number of denoising steps for validation inference
  # Higher values = better quality but slower generation
  inference_steps: 30
  # Generate validation videos every N training steps
  # Set to null to disable validation during training
  interval: 100
  # Classifier-free guidance scale
  # Higher values = stronger adherence to prompt but may introduce artifacts
  guidance_scale: 4.0
  # STG (Spatio-Temporal Guidance) parameters for improved video quality
  # STG is combined with CFG for better temporal coherence
  stg_scale: 1.0  # Recommended: 1.0 (0.0 disables STG)
  stg_blocks: [29]  # Recommended: single block 29
  stg_mode: "stg_v"  # "stg_v" for video-only (no audio training)
  # Whether to generate audio in validation samples
  # Can be enabled even when not training the audio branch
  generate_audio: false
  # Skip validation at the beginning of training (step 0)
  skip_initial_validation: false
 # -----------------------------------------------------------------------------
 # Checkpoint Configuration
 # -----------------------------------------------------------------------------
 # Controls model checkpoint saving during training.
 checkpoints:
  # Save a checkpoint every N steps
  # Set to null to disable intermediate checkpoints
  interval: 250
  # Number of most recent checkpoints to keep
  # Set to -1 to keep all checkpoints
  keep_last_n: 3
  # Precision to use when saving checkpoint weights
  # Options: "bfloat16" (default, smaller files) or "float32" (full precision)
  precision: "bfloat16"
 # -----------------------------------------------------------------------------
 # Flow Matching Configuration
 # -----------------------------------------------------------------------------
 # Parameters for the flow matching training objective.
 flow_matching:
  # Timestep sampling mode
  # "shifted_logit_normal" is recommended for LTX-2 models
  timestep_sampling_mode: "shifted_logit_normal"
  # Additional parameters for timestep sampling
  timestep_sampling_params: { }
 # -----------------------------------------------------------------------------
 # Hugging Face Hub Configuration
 # -----------------------------------------------------------------------------
 # Settings for uploading trained models to the Hugging Face Hub.
 hub:
  # Whether to push the trained model to the Hub
  push_to_hub: false
  # Repository ID on Hugging Face Hub (e.g., "username/my-ic-lora-model")
  # Required if push_to_hub is true
  hub_model_id: null
 # -----------------------------------------------------------------------------
 # Weights & Biases Configuration
 # -----------------------------------------------------------------------------
 # Settings for experiment tracking with W&B.
 wandb:
  # Enable W&B logging
  enabled: false
  # W&B project name
  project: "ltx-2-trainer"
  # W&B username or team (null uses default account)
  entity: null
  # Tags to help organize runs
  tags: [ "ltx2", "ic-lora", "v2v" ]
  # Log validation media (video/audio) to W&B
  log_validation_videos: true
 # -----------------------------------------------------------------------------
 # General Configuration
 # -----------------------------------------------------------------------------
 # Global settings for the training run.
 # Random seed for reproducibility
 seed: 42
 # Directory to save outputs (checkpoints, validation videos, logs)
 output_dir: "outputs/v2v_ic_lora"
@@ -1,355 +0,0 @@
 # =============================================================================
 # LTX-2 Video Extension LoRA Training Configuration
 # =============================================================================
 #
 # This configuration is for training LoRA adapters on the LTX-2 model for
 # video extension (temporal continuation). The model learns to extend a video
 # forward in time by conditioning on a prefix of existing frames.
 #
 # Prefix conditioning works by providing the first N temporal units as clean
 # conditioning signals during training — they receive no noise, timestep=0,
 # and are excluded from the loss. The model learns to generate continuation
 # frames that seamlessly follow the given prefix.
 #
 # Use this configuration when you want to:
 #   - Train the model to extend/continue existing videos
 #   - Fine-tune temporal continuation capabilities on custom datasets
 #   - Create seamless video extension models with optional audio
 #
 # Dataset structure:
 #   preprocessed_data_root/
 #   ├── latents/        # Video latents (VAE-encoded videos)
 #   ├── conditions/     # Text embeddings for each video
 #   └── audio_latents/  # Audio latents (VAE-encoded audio)
 #
 # =============================================================================
 # -----------------------------------------------------------------------------
 # Model Configuration
 # -----------------------------------------------------------------------------
 # Specifies the base model to fine-tune and the training mode.
 model:
  # Path to the LTX-2 model checkpoint (.safetensors file)
  # This should be a local path to your downloaded model
  model_path: "path/to/ltx-2-model.safetensors"
  # Path to the text encoder model directory
  # For LTX-2, this is typically the Gemma-based text encoder
  text_encoder_path: "path/to/gemma-text-encoder"
  # Training mode: "lora" for efficient adapter training, "full" for full fine-tuning
  # LoRA is recommended for most use cases (faster, less memory, prevents overfitting)
  training_mode: "lora"
  # Optional: Path to resume training from a checkpoint
  # Can be a checkpoint file (.safetensors) or directory (uses latest checkpoint)
  load_checkpoint: null
 # -----------------------------------------------------------------------------
 # LoRA Configuration
 # -----------------------------------------------------------------------------
 # Controls the Low-Rank Adaptation parameters for efficient fine-tuning.
 lora:
  # Rank of the LoRA matrices (higher = more capacity but more parameters)
  # Typical values: 8, 16, 32, 64. Start with 32 for general fine-tuning.
  rank: 32
  # Alpha scaling factor (usually set equal to rank)
  # The effective scaling is alpha/rank, so alpha=rank means scaling of 1.0
  alpha: 32
  # Dropout probability for LoRA layers (0.0 = no dropout)
  # Can help with regularization if overfitting occurs
  dropout: 0.0
  # Which transformer modules to apply LoRA to
  # The LTX-2 transformer has separate attention and FFN blocks for video and audio:
  #
  # VIDEO MODULES:
  #   - attn1.to_k, attn1.to_q, attn1.to_v, attn1.to_out.0  (video self-attention)
  #   - attn2.to_k, attn2.to_q, attn2.to_v, attn2.to_out.0  (video cross-attention to text)
  #   - ff.net.0.proj, ff.net.2                             (video feed-forward)
  #
  # AUDIO MODULES:
  #   - audio_attn1.to_k, audio_attn1.to_q, audio_attn1.to_v, audio_attn1.to_out.0  (audio self-attention)
  #   - audio_attn2.to_k, audio_attn2.to_q, audio_attn2.to_v, audio_attn2.to_out.0  (audio cross-attention to text)
  #   - audio_ff.net.0.proj, audio_ff.net.2                                         (audio feed-forward)
  #
  # AUDIO-VIDEO CROSS-ATTENTION MODULES (for cross-modal interaction):
  #   - audio_to_video_attn.to_k, audio_to_video_attn.to_q, audio_to_video_attn.to_v, audio_to_video_attn.to_out.0
  #       (Q from video, K/V from audio - allows video to attend to audio features)
  #   - video_to_audio_attn.to_k, video_to_audio_attn.to_q, video_to_audio_attn.to_v, video_to_audio_attn.to_out.0
  #       (Q from audio, K/V from video - allows audio to attend to video features)
  #
  # Using short patterns like "to_k" matches ALL attention modules (video, audio, and cross-modal).
  # For audio-video training, this is the recommended approach.
  target_modules:
    # Attention layers (matches both video and audio branches)
    - "to_k"
    - "to_q"
    - "to_v"
    - "to_out.0"
    # Uncomment below to also train feed-forward layers (can increase the LoRA's capacity):
    # - "ff.net.0.proj"
    # - "ff.net.2"
    # - "audio_ff.net.0.proj"
    # - "audio_ff.net.2"
 # -----------------------------------------------------------------------------
 # Training Strategy Configuration
 # -----------------------------------------------------------------------------
 # Defines the video extension training approach using the unified flexible strategy.
 # Prefix conditioning provides the first N latent frames as clean conditioning,
 # teaching the model to generate temporally coherent continuations.
 training_strategy:
  # Strategy name: "flexible" for the unified conditioning framework
  # Supports all training modes (T2V, I2V, V2V, A2V, V2A, etc.) through
  # modality-specific configuration blocks.
  name: "flexible"
  # Video modality configuration
  video:
    # Whether the model generates video (true) or uses it as frozen conditioning (false)
    is_generated: true
    # Directory name (within preprocessed_data_root) containing video latents
    latents_dir: "latents"
    # Conditions applied to the video modality during training
    # Prefix conditioning: the first N temporal units are provided as clean
    # conditioning signals (no noise, timestep=0, excluded from loss)
    conditions:
      - type: prefix
        # Number of latent frames to use as conditioning prefix
        # For prefix conditioning, N latent frames correspond to (N - 1) * 8 + 1 pixel frames.
        # temporal_boundary=8 means 57 pixel frames are used as prefix.
        temporal_boundary: 8
        # Probability of applying prefix conditioning per training sample
        # At 1.0, all training samples use video extension mode
        probability: 1.0
  # Audio modality configuration
  audio:
    # Whether the model generates audio (true) or uses it as frozen conditioning (false)
    is_generated: true
    # Directory name (within preprocessed_data_root) containing audio latents
    latents_dir: "audio_latents"
 # -----------------------------------------------------------------------------
 # Optimization Configuration
 # -----------------------------------------------------------------------------
 # Controls the training optimization parameters.
 optimization:
  # Learning rate for the optimizer
  # Typical range for LoRA: 1e-5 to 1e-4
  learning_rate: 1e-4
  # Total number of training steps
  steps: 2000
  # Batch size per GPU
  # Reduce if running out of memory
  batch_size: 1
  # Number of gradient accumulation steps
  # Effective batch size = batch_size * gradient_accumulation_steps * num_gpus
  gradient_accumulation_steps: 1
  # Maximum gradient norm for clipping (helps training stability)
  max_grad_norm: 1.0
  # Optimizer type: "adamw" (standard) or "adamw8bit" (memory-efficient)
  optimizer_type: "adamw"
  # Learning rate scheduler type
  # Options: "constant", "linear", "cosine", "cosine_with_restarts", "polynomial"
  scheduler_type: "linear"
  # Additional scheduler parameters (depends on scheduler_type)
  scheduler_params: { }
  # Enable gradient checkpointing to reduce memory usage
  # Recommended for training with limited GPU memory
  enable_gradient_checkpointing: true
 # -----------------------------------------------------------------------------
 # Acceleration Configuration
 # -----------------------------------------------------------------------------
 # Hardware acceleration and memory optimization settings.
 acceleration:
  # Mixed precision training mode
  # Options: "no" (fp32), "fp16" (half precision), "bf16" (bfloat16, recommended)
  mixed_precision_mode: "bf16"
  # Model quantization for reduced memory usage
  # Options: null (none), "int8-quanto", "int4-quanto", "int2-quanto", "fp8-quanto", "fp8uz-quanto"
  quantization: null
  # Load text encoder in 8-bit precision to save memory
  # Useful when GPU memory is limited
  load_text_encoder_in_8bit: false
  # Offload optimizer state to CPU during validation video sampling and restore it after.
  # Frees VRAM for the VAE decoder when optimizer state is large (full fine-tune, high-rank
  # LoRA). No effect under FSDP (sharded state).
  offload_optimizer_during_validation: false
 # -----------------------------------------------------------------------------
 # Data Configuration
 # -----------------------------------------------------------------------------
 # Specifies the training data location and loading parameters.
 data:
  # Root directory containing preprocessed training data
  # Should contain: latents/, conditions/, and audio_latents/
  preprocessed_data_root: "/path/to/preprocessed/data"
  # Number of worker processes for data loading
  # Used for parallel data loading to speed up data loading
  num_dataloader_workers: 2
 # -----------------------------------------------------------------------------
 # Validation Configuration
 # -----------------------------------------------------------------------------
 # Controls validation sampling during training.
 # NOTE: Validation sampling use simplified inference pipelines and prioritizes speed over
 # maximum quality. For production-quality inference, use `packages/ltx-pipelines`.
 validation:
  # Validation samples — each sample describes a self-contained generation request.
  # Use 'conditions' to add conditioning (first_frame, prefix, suffix, reference, video_to_audio, etc.)
  # See docs/configuration-reference.md#validation-condition-types for the full list of condition types.
  samples:
    - prompt: >-
        A woman with long brown hair sits at a wooden desk in a cozy home office, typing on a
        laptop while occasionally glancing at notes beside her. Soft natural light streams through
        a large window, casting warm shadows across the room. She pauses to take a sip from a
        ceramic mug, then continues working with focused concentration. The audio captures the
        gentle clicking of keyboard keys, the soft rustle of papers, and ambient room tone with
        occasional distant bird chirps from outside.
      conditions:
        - type: prefix
          video: "/path/to/prefix_video_1.mp4"
          # Matches temporal_boundary=8 during training: (8 - 1) * 8 + 1 = 57 frames
          num_frames: 57
    - prompt: >-
        A chef in a white uniform stands in a professional kitchen, carefully plating a gourmet
        dish with precise movements. Steam rises from freshly cooked vegetables as he arranges
        them with tweezers. The stainless steel surfaces gleam under bright overhead lights, and
        various pots simmer on the stove behind him. The audio features the sizzling of pans,
        the clinking of utensils against plates, and the ambient hum of kitchen ventilation.
      conditions:
        - type: prefix
          video: "/path/to/prefix_video_2.mp4"
          # Matches temporal_boundary=8 during training: (8 - 1) * 8 + 1 = 57 frames
          num_frames: 57
  # Negative prompt to avoid unwanted artifacts
  negative_prompt: "worst quality, inconsistent motion, blurry, jittery, distorted"
  # Output video dimensions [width, height, frames]
  # Width and height must be divisible by 32
  # Frames must satisfy: frames % 8 == 1 (e.g., 1, 9, 17, 25, 33, 41, 49, 57, 65, 73, 81, 89, ...)
  video_dims: [ 576, 576, 89 ]
  # Frame rate for generated videos
  frame_rate: 25.0
  # Random seed for reproducible validation outputs
  seed: 42
  # Number of denoising steps for validation inference
  # Higher values = better quality but slower generation
  inference_steps: 30
  # Generate validation videos every N training steps
  # Set to null to disable validation during training
  interval: 100
  # Classifier-free guidance scale
  # Higher values = stronger adherence to prompt but may introduce artifacts
  guidance_scale: 4.0
  # STG (Spatio-Temporal Guidance) parameters for improved video quality
  # STG is combined with CFG for better temporal coherence
  stg_scale: 1.0  # Recommended: 1.0 (0.0 disables STG)
  stg_blocks: [29]  # Recommended: single block 29
  stg_mode: "stg_av"  # "stg_av" perturbs both audio and video, "stg_v" video only
  # Whether to generate audio in validation samples
  # Independent of training_strategy.audio.is_generated - you can generate audio
  # in validation even when not training the audio branch
  generate_audio: true
  # Skip validation at the beginning of training (step 0)
  skip_initial_validation: false
 # -----------------------------------------------------------------------------
 # Checkpoint Configuration
 # -----------------------------------------------------------------------------
 # Controls model checkpoint saving during training.
 checkpoints:
  # Save a checkpoint every N steps
  # Set to null to disable intermediate checkpoints
  interval: 250
  # Number of most recent checkpoints to keep
  # Set to -1 to keep all checkpoints
  keep_last_n: -1
  # Precision to use when saving checkpoint weights
  # Options: "bfloat16" (default, smaller files) or "float32" (full precision)
  precision: "bfloat16"
 # -----------------------------------------------------------------------------
 # Flow Matching Configuration
 # -----------------------------------------------------------------------------
 # Parameters for the flow matching training objective.
 flow_matching:
  # Timestep sampling mode
  # "shifted_logit_normal" is recommended for LTX-2 models
  timestep_sampling_mode: "shifted_logit_normal"
  # Additional parameters for timestep sampling
  timestep_sampling_params: { }
 # -----------------------------------------------------------------------------
 # Hugging Face Hub Configuration
 # -----------------------------------------------------------------------------
 # Settings for uploading trained models to the Hugging Face Hub.
 hub:
  # Whether to push the trained model to the Hub
  push_to_hub: false
  # Repository ID on Hugging Face Hub (e.g., "username/my-lora-model")
  # Required if push_to_hub is true
  hub_model_id: null
 # -----------------------------------------------------------------------------
 # Weights & Biases Configuration
 # -----------------------------------------------------------------------------
 # Settings for experiment tracking with W&B.
 wandb:
  # Enable W&B logging
  enabled: false
  # W&B project name
  project: "ltx-2-trainer"
  # W&B username or team (null uses default account)
  entity: null
  # Tags to help organize runs
  tags: [ "ltx2", "lora", "video-extension" ]
  # Log validation media (video/audio) to W&B
  log_validation_videos: true
 # -----------------------------------------------------------------------------
 # General Configuration
 # -----------------------------------------------------------------------------
 # Global settings for the training run.
 # Random seed for reproducibility
 seed: 42
 # Directory to save outputs (checkpoints, validation videos, logs)
 output_dir: "outputs/video_extend_lora"
@@ -1,343 +0,0 @@
 # =============================================================================
 # LTX-2 Video Inpainting LoRA Training Configuration
 # =============================================================================
 #
 # This configuration is for training LoRA adapters on the LTX-2 model for
 # video inpainting. The model learns to fill in masked regions of a video
 # using per-sample binary masks that define which regions are conditioning
 # (provided clean) and which regions the model must generate.
 #
 # Mask conditioning works by loading per-sample binary masks from disk.
 # Masked regions receive clean latents (no noise, timestep=0) and are excluded
 # from the loss. Unmasked regions are noised and trained normally.
 #
 # Use this configuration when you want to:
 #   - Train the model to fill in or replace regions of existing videos
 #   - Fine-tune video inpainting capabilities on custom datasets
 #   - Create object removal or region editing models
 #
 # Dataset structure:
 #   preprocessed_data_root/
 #   ├── latents/        # Video latents (VAE-encoded videos)
 #   ├── conditions/     # Text embeddings for each video
 #   └── video_masks/    # Per-sample binary masks defining conditioning regions
 #
 # Dataset metadata columns: video, video_mask, caption
 #
 # =============================================================================
 # -----------------------------------------------------------------------------
 # Model Configuration
 # -----------------------------------------------------------------------------
 # Specifies the base model to fine-tune and the training mode.
 model:
  # Path to the LTX-2 model checkpoint (.safetensors file)
  # This should be a local path to your downloaded model
  model_path: "path/to/ltx-2-model.safetensors"
  # Path to the text encoder model directory
  # For LTX-2, this is typically the Gemma-based text encoder
  text_encoder_path: "path/to/gemma-text-encoder"
  # Training mode: "lora" for efficient adapter training, "full" for full fine-tuning
  # LoRA is recommended for most use cases (faster, less memory, prevents overfitting)
  training_mode: "lora"
  # Optional: Path to resume training from a checkpoint
  # Can be a checkpoint file (.safetensors) or directory (uses latest checkpoint)
  load_checkpoint: null
 # -----------------------------------------------------------------------------
 # LoRA Configuration
 # -----------------------------------------------------------------------------
 # Controls the Low-Rank Adaptation parameters for efficient fine-tuning.
 lora:
  # Rank of the LoRA matrices (higher = more capacity but more parameters)
  # Typical values: 8, 16, 32, 64. Start with 32 for general fine-tuning.
  rank: 32
  # Alpha scaling factor (usually set equal to rank)
  # The effective scaling is alpha/rank, so alpha=rank means scaling of 1.0
  alpha: 32
  # Dropout probability for LoRA layers (0.0 = no dropout)
  # Can help with regularization if overfitting occurs
  dropout: 0.0
  # Which transformer modules to apply LoRA to
  # The LTX-2 transformer has separate attention and FFN blocks for video and audio:
  #
  # VIDEO MODULES:
  #   - attn1.to_k, attn1.to_q, attn1.to_v, attn1.to_out.0  (video self-attention)
  #   - attn2.to_k, attn2.to_q, attn2.to_v, attn2.to_out.0  (video cross-attention to text)
  #   - ff.net.0.proj, ff.net.2                             (video feed-forward)
  #
  # AUDIO MODULES:
  #   - audio_attn1.to_k, audio_attn1.to_q, audio_attn1.to_v, audio_attn1.to_out.0  (audio self-attention)
  #   - audio_attn2.to_k, audio_attn2.to_q, audio_attn2.to_v, audio_attn2.to_out.0  (audio cross-attention to text)
  #   - audio_ff.net.0.proj, audio_ff.net.2                                         (audio feed-forward)
  #
  # AUDIO-VIDEO CROSS-ATTENTION MODULES (for cross-modal interaction):
  #   - audio_to_video_attn.to_k, audio_to_video_attn.to_q, audio_to_video_attn.to_v, audio_to_video_attn.to_out.0
  #       (Q from video, K/V from audio - allows video to attend to audio features)
  #   - video_to_audio_attn.to_k, video_to_audio_attn.to_q, video_to_audio_attn.to_v, video_to_audio_attn.to_out.0
  #       (Q from audio, K/V from video - allows audio to attend to video features)
  #
  # This is a video-only config, so explicitly target video attention modules.
  target_modules:
    - "attn1.to_k"
    - "attn1.to_q"
    - "attn1.to_v"
    - "attn1.to_out.0"
    - "attn2.to_k"
    - "attn2.to_q"
    - "attn2.to_v"
    - "attn2.to_out.0"
    # Uncomment below to also train feed-forward layers (can increase the LoRA's capacity):
    # - "ff.net.0.proj"
    # - "ff.net.2"
 # -----------------------------------------------------------------------------
 # Training Strategy Configuration
 # -----------------------------------------------------------------------------
 # Defines the video inpainting training approach using the unified flexible
 # strategy. Per-sample binary masks define which regions are provided as clean
 # conditioning and which regions the model must learn to generate.
 training_strategy:
  # Strategy name: "flexible" for the unified conditioning framework
  # Supports all training modes (T2V, I2V, V2V, A2V, V2A, etc.) through
  # modality-specific configuration blocks.
  name: "flexible"
  # Video modality configuration
  video:
    # Whether the model generates video (true) or uses it as frozen conditioning (false)
    is_generated: true
    # Directory name (within preprocessed_data_root) containing video latents
    latents_dir: "latents"
    # Conditions applied to the video modality during training
    # Mask conditioning: per-sample binary masks loaded from disk define which
    # tokens are conditioning (clean, timestep=0, no loss) vs generated
    conditions:
      - type: mask
        # Directory name (within preprocessed_data_root) containing binary masks
        # Each mask file corresponds to a training sample and defines the
        # conditioning region (mask=1 means conditioning, mask=0 means generate)
        mask_dir: "video_masks"
        # Probability of applying mask conditioning per training sample
        # At 1.0, all training samples use inpainting mode
        probability: 1.0
 # -----------------------------------------------------------------------------
 # Optimization Configuration
 # -----------------------------------------------------------------------------
 # Controls the training optimization parameters.
 optimization:
  # Learning rate for the optimizer
  # Typical range for LoRA: 1e-5 to 1e-4
  learning_rate: 1e-4
  # Total number of training steps
  steps: 2000
  # Batch size per GPU
  # Reduce if running out of memory
  batch_size: 1
  # Number of gradient accumulation steps
  # Effective batch size = batch_size * gradient_accumulation_steps * num_gpus
  gradient_accumulation_steps: 1
  # Maximum gradient norm for clipping (helps training stability)
  max_grad_norm: 1.0
  # Optimizer type: "adamw" (standard) or "adamw8bit" (memory-efficient)
  optimizer_type: "adamw"
  # Learning rate scheduler type
  # Options: "constant", "linear", "cosine", "cosine_with_restarts", "polynomial"
  scheduler_type: "linear"
  # Additional scheduler parameters (depends on scheduler_type)
  scheduler_params: { }
  # Enable gradient checkpointing to reduce memory usage
  # Recommended for training with limited GPU memory
  enable_gradient_checkpointing: true
 # -----------------------------------------------------------------------------
 # Acceleration Configuration
 # -----------------------------------------------------------------------------
 # Hardware acceleration and memory optimization settings.
 acceleration:
  # Mixed precision training mode
  # Options: "no" (fp32), "fp16" (half precision), "bf16" (bfloat16, recommended)
  mixed_precision_mode: "bf16"
  # Model quantization for reduced memory usage
  # Options: null (none), "int8-quanto", "int4-quanto", "int2-quanto", "fp8-quanto", "fp8uz-quanto"
  quantization: null
  # Load text encoder in 8-bit precision to save memory
  # Useful when GPU memory is limited
  load_text_encoder_in_8bit: false
  # Offload optimizer state to CPU during validation video sampling and restore it after.
  # Frees VRAM for the VAE decoder when optimizer state is large (full fine-tune, high-rank
  # LoRA). No effect under FSDP (sharded state).
  offload_optimizer_during_validation: false
 # -----------------------------------------------------------------------------
 # Data Configuration
 # -----------------------------------------------------------------------------
 # Specifies the training data location and loading parameters.
 data:
  # Root directory containing preprocessed training data
  # Should contain: latents/, conditions/, and video_masks/
  preprocessed_data_root: "/path/to/preprocessed/data"
  # Number of worker processes for data loading
  # Used for parallel data loading to speed up data loading
  num_dataloader_workers: 2
 # -----------------------------------------------------------------------------
 # Validation Configuration
 # -----------------------------------------------------------------------------
 # Controls validation sampling during training.
 # NOTE: Validation sampling use simplified inference pipelines and prioritizes speed over
 # maximum quality. For production-quality inference, use `packages/ltx-pipelines`.
 validation:
  # Validation samples — each sample describes a self-contained generation request.
  # Use 'conditions' to add conditioning (first_frame, prefix, suffix, reference, video_to_audio, etc.)
  # See docs/configuration-reference.md#validation-condition-types for the full list of condition types.
  samples:
    - prompt: >-
        A woman with long brown hair sits at a wooden desk in a cozy home office, typing on a
        laptop while occasionally glancing at notes beside her. Soft natural light streams through
        a large window, casting warm shadows across the room. She pauses to take a sip from a
        ceramic mug, then continues working with focused concentration.
      conditions:
        - type: mask
          video: "/path/to/inpainting_video_1.mp4"
          mask: "/path/to/inpainting_mask_1.mp4"
    - prompt: >-
        A chef in a white uniform stands in a professional kitchen, carefully plating a gourmet
        dish with precise movements. Steam rises from freshly cooked vegetables as he arranges
        them with tweezers. The stainless steel surfaces gleam under bright overhead lights, and
        various pots simmer on the stove behind him.
      conditions:
        - type: mask
          video: "/path/to/inpainting_video_2.mp4"
          mask: "/path/to/inpainting_mask_2.mp4"
  # Negative prompt to avoid unwanted artifacts
  negative_prompt: "worst quality, inconsistent motion, blurry, jittery, distorted"
  # Output video dimensions [width, height, frames]
  # Width and height must be divisible by 32
  # Frames must satisfy: frames % 8 == 1 (e.g., 1, 9, 17, 25, 33, 41, 49, 57, 65, 73, 81, 89, ...)
  video_dims: [ 576, 576, 89 ]
  # Frame rate for generated videos
  frame_rate: 25.0
  # Random seed for reproducible validation outputs
  seed: 42
  # Number of denoising steps for validation inference
  # Higher values = better quality but slower generation
  inference_steps: 30
  # Generate validation videos every N training steps
  # Set to null to disable validation during training
  interval: 100
  # Classifier-free guidance scale
  # Higher values = stronger adherence to prompt but may introduce artifacts
  guidance_scale: 4.0
  # STG (Spatio-Temporal Guidance) parameters for improved video quality
  # STG is combined with CFG for better temporal coherence
  stg_scale: 1.0  # Recommended: 1.0 (0.0 disables STG)
  stg_blocks: [29]  # Recommended: single block 29
  stg_mode: "stg_v"  # "stg_v" for video-only validation
  # Video inpainting trains video only; do not generate validation audio.
  generate_audio: false
  # Skip validation at the beginning of training (step 0)
  skip_initial_validation: false
 # -----------------------------------------------------------------------------
 # Checkpoint Configuration
 # -----------------------------------------------------------------------------
 # Controls model checkpoint saving during training.
 checkpoints:
  # Save a checkpoint every N steps
  # Set to null to disable intermediate checkpoints
  interval: 250
  # Number of most recent checkpoints to keep
  # Set to -1 to keep all checkpoints
  keep_last_n: -1
  # Precision to use when saving checkpoint weights
  # Options: "bfloat16" (default, smaller files) or "float32" (full precision)
  precision: "bfloat16"
 # -----------------------------------------------------------------------------
 # Flow Matching Configuration
 # -----------------------------------------------------------------------------
 # Parameters for the flow matching training objective.
 flow_matching:
  # Timestep sampling mode
  # "shifted_logit_normal" is recommended for LTX-2 models
  timestep_sampling_mode: "shifted_logit_normal"
  # Additional parameters for timestep sampling
  timestep_sampling_params: { }
 # -----------------------------------------------------------------------------
 # Hugging Face Hub Configuration
 # -----------------------------------------------------------------------------
 # Settings for uploading trained models to the Hugging Face Hub.
 hub:
  # Whether to push the trained model to the Hub
  push_to_hub: false
  # Repository ID on Hugging Face Hub (e.g., "username/my-lora-model")
  # Required if push_to_hub is true
  hub_model_id: null
 # -----------------------------------------------------------------------------
 # Weights & Biases Configuration
 # -----------------------------------------------------------------------------
 # Settings for experiment tracking with W&B.
 wandb:
  # Enable W&B logging
  enabled: false
  # W&B project name
  project: "ltx-2-trainer"
  # W&B username or team (null uses default account)
  entity: null
  # Tags to help organize runs
  tags: [ "ltx2", "lora", "inpainting" ]
  # Log validation outputs to W&B
  log_validation_videos: true
 # -----------------------------------------------------------------------------
 # General Configuration
 # -----------------------------------------------------------------------------
 # Global settings for the training run.
 # Random seed for reproducibility
 seed: 42
 # Directory to save outputs (checkpoints, validation videos, logs)
 output_dir: "outputs/video_inpainting_lora"
@@ -1,341 +0,0 @@
 # =============================================================================
 # LTX-2 Video Outpainting LoRA Training Configuration
 # =============================================================================
 #
 # This configuration is for training LoRA adapters on the LTX-2 model for
 # video outpainting (spatial extension). The model learns to generate content
 # surrounding a known rectangular region of the video.
 #
 # Spatial crop conditioning works by providing a rectangular pixel region as
 # clean conditioning during training — those tokens receive no noise,
 # timestep=0, and are excluded from the loss. The model learns to generate
 # the content outside the given region, seamlessly extending the scene.
 #
 # Use this configuration when you want to:
 #   - Extend video content beyond its original boundaries
 #   - Train spatial outpainting capabilities on custom datasets
 #   - Create video aspect ratio conversion models
 #
 # Dataset structure:
 #   preprocessed_data_root/
 #   ├── latents/        # Video latents (VAE-encoded videos)
 #   └── conditions/     # Text embeddings for each video
 #
 # =============================================================================
 # -----------------------------------------------------------------------------
 # Model Configuration
 # -----------------------------------------------------------------------------
 # Specifies the base model to fine-tune and the training mode.
 model:
  # Path to the LTX-2 model checkpoint (.safetensors file)
  # This should be a local path to your downloaded model
  model_path: "path/to/ltx-2-model.safetensors"
  # Path to the text encoder model directory
  # For LTX-2, this is typically the Gemma-based text encoder
  text_encoder_path: "path/to/gemma-text-encoder"
  # Training mode: "lora" for efficient adapter training, "full" for full fine-tuning
  # LoRA is recommended for most use cases (faster, less memory, prevents overfitting)
  training_mode: "lora"
  # Optional: Path to resume training from a checkpoint
  # Can be a checkpoint file (.safetensors) or directory (uses latest checkpoint)
  load_checkpoint: null
 # -----------------------------------------------------------------------------
 # LoRA Configuration
 # -----------------------------------------------------------------------------
 # Controls the Low-Rank Adaptation parameters for efficient fine-tuning.
 lora:
  # Rank of the LoRA matrices (higher = more capacity but more parameters)
  # Typical values: 8, 16, 32, 64. Start with 32 for general fine-tuning.
  rank: 32
  # Alpha scaling factor (usually set equal to rank)
  # The effective scaling is alpha/rank, so alpha=rank means scaling of 1.0
  alpha: 32
  # Dropout probability for LoRA layers (0.0 = no dropout)
  # Can help with regularization if overfitting occurs
  dropout: 0.0
  # Which transformer modules to apply LoRA to
  # The LTX-2 transformer has separate attention and FFN blocks for video and audio:
  #
  # VIDEO MODULES:
  #   - attn1.to_k, attn1.to_q, attn1.to_v, attn1.to_out.0  (video self-attention)
  #   - attn2.to_k, attn2.to_q, attn2.to_v, attn2.to_out.0  (video cross-attention to text)
  #   - ff.net.0.proj, ff.net.2                             (video feed-forward)
  #
  # AUDIO MODULES:
  #   - audio_attn1.to_k, audio_attn1.to_q, audio_attn1.to_v, audio_attn1.to_out.0  (audio self-attention)
  #   - audio_attn2.to_k, audio_attn2.to_q, audio_attn2.to_v, audio_attn2.to_out.0  (audio cross-attention to text)
  #   - audio_ff.net.0.proj, audio_ff.net.2                                         (audio feed-forward)
  #
  # AUDIO-VIDEO CROSS-ATTENTION MODULES (for cross-modal interaction):
  #   - audio_to_video_attn.to_k, audio_to_video_attn.to_q, audio_to_video_attn.to_v, audio_to_video_attn.to_out.0
  #       (Q from video, K/V from audio - allows video to attend to audio features)
  #   - video_to_audio_attn.to_k, video_to_audio_attn.to_q, video_to_audio_attn.to_v, video_to_audio_attn.to_out.0
  #       (Q from audio, K/V from video - allows audio to attend to video features)
  #
  # This is a video-only config, so explicitly target video attention modules.
  target_modules:
    - "attn1.to_k"
    - "attn1.to_q"
    - "attn1.to_v"
    - "attn1.to_out.0"
    - "attn2.to_k"
    - "attn2.to_q"
    - "attn2.to_v"
    - "attn2.to_out.0"
    # Uncomment below to also train feed-forward layers (can increase the LoRA's capacity):
    # - "ff.net.0.proj"
    # - "ff.net.2"
 # -----------------------------------------------------------------------------
 # Training Strategy Configuration
 # -----------------------------------------------------------------------------
 # Defines the video outpainting training approach using the unified flexible
 # strategy. Spatial crop conditioning provides a rectangular pixel region as
 # clean conditioning, teaching the model to generate surrounding content.
 training_strategy:
  # Strategy name: "flexible" for the unified conditioning framework
  # Supports all training modes (T2V, I2V, V2V, A2V, V2A, etc.) through
  # modality-specific configuration blocks.
  name: "flexible"
  # Video modality configuration
  video:
    # Whether the model generates video (true) or uses it as frozen conditioning (false)
    is_generated: true
    # Directory name (within preprocessed_data_root) containing video latents
    latents_dir: "latents"
    # Conditions applied to the video modality during training
    # Spatial crop conditioning provides a rectangular region as clean context;
    # the model learns to generate the surrounding video tokens.
    conditions:
      - type: spatial_crop
        # Rectangular pixel region provided as clean conditioning (y1, x1, y2, x2)
        # Pixels within this region are conditioning (clean, timestep=0, no loss)
        # Pixels outside this region are generated by the model
        # Coordinates are in pixel space — automatically converted to latent space
        spatial_region: [0, 0, 288, 576]
        # Probability of applying spatial crop conditioning per training sample
        # At 1.0, all training samples use outpainting mode
        probability: 1.0
 # -----------------------------------------------------------------------------
 # Optimization Configuration
 # -----------------------------------------------------------------------------
 # Controls the training optimization parameters.
 optimization:
  # Learning rate for the optimizer
  # Typical range for LoRA: 1e-5 to 1e-4
  learning_rate: 1e-4
  # Total number of training steps
  steps: 2000
  # Batch size per GPU
  # Reduce if running out of memory
  batch_size: 1
  # Number of gradient accumulation steps
  # Effective batch size = batch_size * gradient_accumulation_steps * num_gpus
  gradient_accumulation_steps: 1
  # Maximum gradient norm for clipping (helps training stability)
  max_grad_norm: 1.0
  # Optimizer type: "adamw" (standard) or "adamw8bit" (memory-efficient)
  optimizer_type: "adamw"
  # Learning rate scheduler type
  # Options: "constant", "linear", "cosine", "cosine_with_restarts", "polynomial"
  scheduler_type: "linear"
  # Additional scheduler parameters (depends on scheduler_type)
  scheduler_params: { }
  # Enable gradient checkpointing to reduce memory usage
  # Recommended for training with limited GPU memory
  enable_gradient_checkpointing: true
 # -----------------------------------------------------------------------------
 # Acceleration Configuration
 # -----------------------------------------------------------------------------
 # Hardware acceleration and memory optimization settings.
 acceleration:
  # Mixed precision training mode
  # Options: "no" (fp32), "fp16" (half precision), "bf16" (bfloat16, recommended)
  mixed_precision_mode: "bf16"
  # Model quantization for reduced memory usage
  # Options: null (none), "int8-quanto", "int4-quanto", "int2-quanto", "fp8-quanto", "fp8uz-quanto"
  quantization: null
  # Load text encoder in 8-bit precision to save memory
  # Useful when GPU memory is limited
  load_text_encoder_in_8bit: false
  # Offload optimizer state to CPU during validation video sampling and restore it after.
  # Frees VRAM for the VAE decoder when optimizer state is large (full fine-tune, high-rank
  # LoRA). No effect under FSDP (sharded state).
  offload_optimizer_during_validation: false
 # -----------------------------------------------------------------------------
 # Data Configuration
 # -----------------------------------------------------------------------------
 # Specifies the training data location and loading parameters.
 data:
  # Root directory containing preprocessed training data
  # Should contain: latents/ and conditions/
  preprocessed_data_root: "/path/to/preprocessed/data"
  # Number of worker processes for data loading
  # Used for parallel data loading to speed up data loading
  num_dataloader_workers: 2
 # -----------------------------------------------------------------------------
 # Validation Configuration
 # -----------------------------------------------------------------------------
 # Controls validation sampling during training.
 # NOTE: Validation sampling use simplified inference pipelines and prioritizes speed over
 # maximum quality. For production-quality inference, use `packages/ltx-pipelines`.
 validation:
  # Validation samples — each sample describes a self-contained generation request.
  # Use 'conditions' to add conditioning (first_frame, prefix, suffix, reference, video_to_audio, etc.)
  # See docs/configuration-reference.md#validation-condition-types for the full list of condition types.
  samples:
    - prompt: >-
        A woman with long brown hair sits at a wooden desk in a cozy home office, typing on a
        laptop while occasionally glancing at notes beside her. Soft natural light streams through
        a large window, casting warm shadows across the room. She pauses to take a sip from a
        ceramic mug, then continues working with focused concentration.
      conditions:
        - type: spatial_crop
          video: "/path/to/outpainting_video_1.mp4"
          spatial_region: [0, 0, 288, 576]
    - prompt: >-
        A chef in a white uniform stands in a professional kitchen, carefully plating a gourmet
        dish with precise movements. Steam rises from freshly cooked vegetables as he arranges
        them with tweezers. The stainless steel surfaces gleam under bright overhead lights, and
        various pots simmer on the stove behind him.
      conditions:
        - type: spatial_crop
          video: "/path/to/outpainting_video_2.mp4"
          spatial_region: [0, 0, 288, 576]
  # Negative prompt to avoid unwanted artifacts
  negative_prompt: "worst quality, inconsistent motion, blurry, jittery, distorted"
  # Output video dimensions [width, height, frames]
  # Width and height must be divisible by 32
  # Frames must satisfy: frames % 8 == 1 (e.g., 1, 9, 17, 25, 33, 41, 49, 57, 65, 73, 81, 89, ...)
  video_dims: [ 576, 576, 89 ]
  # Frame rate for generated videos
  frame_rate: 25.0
  # Random seed for reproducible validation outputs
  seed: 42
  # Number of denoising steps for validation inference
  # Higher values = better quality but slower generation
  inference_steps: 30
  # Generate validation videos every N training steps
  # Set to null to disable validation during training
  interval: 100
  # Classifier-free guidance scale
  # Higher values = stronger adherence to prompt but may introduce artifacts
  guidance_scale: 4.0
  # STG (Spatio-Temporal Guidance) parameters for improved video quality
  # STG is combined with CFG for better temporal coherence
  stg_scale: 1.0  # Recommended: 1.0 (0.0 disables STG)
  stg_blocks: [29]  # Recommended: single block 29
  stg_mode: "stg_v"  # "stg_v" for video-only validation
  # Video outpainting trains video only; do not generate validation audio.
  generate_audio: false
  # Skip validation at the beginning of training (step 0)
  skip_initial_validation: false
 # -----------------------------------------------------------------------------
 # Checkpoint Configuration
 # -----------------------------------------------------------------------------
 # Controls model checkpoint saving during training.
 checkpoints:
  # Save a checkpoint every N steps
  # Set to null to disable intermediate checkpoints
  interval: 250
  # Number of most recent checkpoints to keep
  # Set to -1 to keep all checkpoints
  keep_last_n: -1
  # Precision to use when saving checkpoint weights
  # Options: "bfloat16" (default, smaller files) or "float32" (full precision)
  precision: "bfloat16"
 # -----------------------------------------------------------------------------
 # Flow Matching Configuration
 # -----------------------------------------------------------------------------
 # Parameters for the flow matching training objective.
 flow_matching:
  # Timestep sampling mode
  # "shifted_logit_normal" is recommended for LTX-2 models
  timestep_sampling_mode: "shifted_logit_normal"
  # Additional parameters for timestep sampling
  timestep_sampling_params: { }
 # -----------------------------------------------------------------------------
 # Hugging Face Hub Configuration
 # -----------------------------------------------------------------------------
 # Settings for uploading trained models to the Hugging Face Hub.
 hub:
  # Whether to push the trained model to the Hub
  push_to_hub: false
  # Repository ID on Hugging Face Hub (e.g., "username/my-lora-model")
  # Required if push_to_hub is true
  hub_model_id: null
 # -----------------------------------------------------------------------------
 # Weights & Biases Configuration
 # -----------------------------------------------------------------------------
 # Settings for experiment tracking with W&B.
 wandb:
  # Enable W&B logging
  enabled: false
  # W&B project name
  project: "ltx-2-trainer"
  # W&B username or team (null uses default account)
  entity: null
  # Tags to help organize runs
  tags: [ "ltx2", "lora", "outpainting", "spatial-crop" ]
  # Log validation outputs to W&B
  log_validation_videos: true
 # -----------------------------------------------------------------------------
 # General Configuration
 # -----------------------------------------------------------------------------
 # Global settings for the training run.
 # Random seed for reproducibility
 seed: 42
 # Directory to save outputs (checkpoints, validation videos, logs)
 output_dir: "outputs/video_outpainting_lora"
@@ -1,355 +0,0 @@
 # =============================================================================
 # LTX-2 Video Backward Extension (Suffix) LoRA Training Configuration
 # =============================================================================
 #
 # This configuration is for training LoRA adapters on the LTX-2 model for
 # backward video extension. The model learns to generate video content that
 # leads into a given suffix of existing frames.
 #
 # Suffix conditioning works by providing the last N temporal units as clean
 # conditioning signals during training — they receive no noise, timestep=0,
 # and are excluded from the loss. The model learns to generate preceding
 # frames that seamlessly lead into the given suffix.
 #
 # Use this configuration when you want to:
 #   - Train the model to generate "prequel" content for existing videos
 #   - Fine-tune backward temporal continuation capabilities
 #   - Create video backward extension models with optional audio
 #
 # Dataset structure:
 #   preprocessed_data_root/
 #   ├── latents/        # Video latents (VAE-encoded videos)
 #   ├── conditions/     # Text embeddings for each video
 #   └── audio_latents/  # Audio latents (VAE-encoded audio)
 #
 # =============================================================================
 # -----------------------------------------------------------------------------
 # Model Configuration
 # -----------------------------------------------------------------------------
 # Specifies the base model to fine-tune and the training mode.
 model:
  # Path to the LTX-2 model checkpoint (.safetensors file)
  # This should be a local path to your downloaded model
  model_path: "path/to/ltx-2-model.safetensors"
  # Path to the text encoder model directory
  # For LTX-2, this is typically the Gemma-based text encoder
  text_encoder_path: "path/to/gemma-text-encoder"
  # Training mode: "lora" for efficient adapter training, "full" for full fine-tuning
  # LoRA is recommended for most use cases (faster, less memory, prevents overfitting)
  training_mode: "lora"
  # Optional: Path to resume training from a checkpoint
  # Can be a checkpoint file (.safetensors) or directory (uses latest checkpoint)
  load_checkpoint: null
 # -----------------------------------------------------------------------------
 # LoRA Configuration
 # -----------------------------------------------------------------------------
 # Controls the Low-Rank Adaptation parameters for efficient fine-tuning.
 lora:
  # Rank of the LoRA matrices (higher = more capacity but more parameters)
  # Typical values: 8, 16, 32, 64. Start with 32 for general fine-tuning.
  rank: 32
  # Alpha scaling factor (usually set equal to rank)
  # The effective scaling is alpha/rank, so alpha=rank means scaling of 1.0
  alpha: 32
  # Dropout probability for LoRA layers (0.0 = no dropout)
  # Can help with regularization if overfitting occurs
  dropout: 0.0
  # Which transformer modules to apply LoRA to
  # The LTX-2 transformer has separate attention and FFN blocks for video and audio:
  #
  # VIDEO MODULES:
  #   - attn1.to_k, attn1.to_q, attn1.to_v, attn1.to_out.0  (video self-attention)
  #   - attn2.to_k, attn2.to_q, attn2.to_v, attn2.to_out.0  (video cross-attention to text)
  #   - ff.net.0.proj, ff.net.2                             (video feed-forward)
  #
  # AUDIO MODULES:
  #   - audio_attn1.to_k, audio_attn1.to_q, audio_attn1.to_v, audio_attn1.to_out.0  (audio self-attention)
  #   - audio_attn2.to_k, audio_attn2.to_q, audio_attn2.to_v, audio_attn2.to_out.0  (audio cross-attention to text)
  #   - audio_ff.net.0.proj, audio_ff.net.2                                         (audio feed-forward)
  #
  # AUDIO-VIDEO CROSS-ATTENTION MODULES (for cross-modal interaction):
  #   - audio_to_video_attn.to_k, audio_to_video_attn.to_q, audio_to_video_attn.to_v, audio_to_video_attn.to_out.0
  #       (Q from video, K/V from audio - allows video to attend to audio features)
  #   - video_to_audio_attn.to_k, video_to_audio_attn.to_q, video_to_audio_attn.to_v, video_to_audio_attn.to_out.0
  #       (Q from audio, K/V from video - allows audio to attend to video features)
  #
  # Using short patterns like "to_k" matches ALL attention modules (video, audio, and cross-modal).
  # For audio-video training, this is the recommended approach.
  target_modules:
    # Attention layers (matches both video and audio branches)
    - "to_k"
    - "to_q"
    - "to_v"
    - "to_out.0"
    # Uncomment below to also train feed-forward layers (can increase the LoRA's capacity):
    # - "ff.net.0.proj"
    # - "ff.net.2"
    # - "audio_ff.net.0.proj"
    # - "audio_ff.net.2"
 # -----------------------------------------------------------------------------
 # Training Strategy Configuration
 # -----------------------------------------------------------------------------
 # Defines the backward video extension training approach using the unified
 # flexible strategy. Suffix conditioning provides the last N latent frames as
 # clean conditioning, teaching the model to generate content leading into them.
 training_strategy:
  # Strategy name: "flexible" for the unified conditioning framework
  # Supports all training modes (T2V, I2V, V2V, A2V, V2A, etc.) through
  # modality-specific configuration blocks.
  name: "flexible"
  # Video modality configuration
  video:
    # Whether the model generates video (true) or uses it as frozen conditioning (false)
    is_generated: true
    # Directory name (within preprocessed_data_root) containing video latents
    latents_dir: "latents"
    # Conditions applied to the video modality during training
    # Suffix conditioning: the last N temporal units are provided as clean
    # conditioning signals (no noise, timestep=0, excluded from loss)
    conditions:
      - type: suffix
        # Number of latent frames to use as conditioning suffix
        # For suffix conditioning, N latent frames correspond to N * 8 pixel frames.
        # temporal_boundary=8 means the last 64 pixel frames are used as suffix.
        temporal_boundary: 8
        # Probability of applying suffix conditioning per training sample
        # At 1.0, all training samples use backward extension mode
        probability: 1.0
  # Audio modality configuration
  audio:
    # Whether the model generates audio (true) or uses it as frozen conditioning (false)
    is_generated: true
    # Directory name (within preprocessed_data_root) containing audio latents
    latents_dir: "audio_latents"
 # -----------------------------------------------------------------------------
 # Optimization Configuration
 # -----------------------------------------------------------------------------
 # Controls the training optimization parameters.
 optimization:
  # Learning rate for the optimizer
  # Typical range for LoRA: 1e-5 to 1e-4
  learning_rate: 1e-4
  # Total number of training steps
  steps: 2000
  # Batch size per GPU
  # Reduce if running out of memory
  batch_size: 1
  # Number of gradient accumulation steps
  # Effective batch size = batch_size * gradient_accumulation_steps * num_gpus
  gradient_accumulation_steps: 1
  # Maximum gradient norm for clipping (helps training stability)
  max_grad_norm: 1.0
  # Optimizer type: "adamw" (standard) or "adamw8bit" (memory-efficient)
  optimizer_type: "adamw"
  # Learning rate scheduler type
  # Options: "constant", "linear", "cosine", "cosine_with_restarts", "polynomial"
  scheduler_type: "linear"
  # Additional scheduler parameters (depends on scheduler_type)
  scheduler_params: { }
  # Enable gradient checkpointing to reduce memory usage
  # Recommended for training with limited GPU memory
  enable_gradient_checkpointing: true
 # -----------------------------------------------------------------------------
 # Acceleration Configuration
 # -----------------------------------------------------------------------------
 # Hardware acceleration and memory optimization settings.
 acceleration:
  # Mixed precision training mode
  # Options: "no" (fp32), "fp16" (half precision), "bf16" (bfloat16, recommended)
  mixed_precision_mode: "bf16"
  # Model quantization for reduced memory usage
  # Options: null (none), "int8-quanto", "int4-quanto", "int2-quanto", "fp8-quanto", "fp8uz-quanto"
  quantization: null
  # Load text encoder in 8-bit precision to save memory
  # Useful when GPU memory is limited
  load_text_encoder_in_8bit: false
  # Offload optimizer state to CPU during validation video sampling and restore it after.
  # Frees VRAM for the VAE decoder when optimizer state is large (full fine-tune, high-rank
  # LoRA). No effect under FSDP (sharded state).
  offload_optimizer_during_validation: false
 # -----------------------------------------------------------------------------
 # Data Configuration
 # -----------------------------------------------------------------------------
 # Specifies the training data location and loading parameters.
 data:
  # Root directory containing preprocessed training data
  # Should contain: latents/, conditions/, and audio_latents/
  preprocessed_data_root: "/path/to/preprocessed/data"
  # Number of worker processes for data loading
  # Used for parallel data loading to speed up data loading
  num_dataloader_workers: 2
 # -----------------------------------------------------------------------------
 # Validation Configuration
 # -----------------------------------------------------------------------------
 # Controls validation sampling during training.
 # NOTE: Validation sampling use simplified inference pipelines and prioritizes speed over
 # maximum quality. For production-quality inference, use `packages/ltx-pipelines`.
 validation:
  # Validation samples — each sample describes a self-contained generation request.
  # Use 'conditions' to add conditioning (first_frame, prefix, suffix, reference, video_to_audio, etc.)
  # See docs/configuration-reference.md#validation-condition-types for the full list of condition types.
  samples:
    - prompt: >-
        A woman with long brown hair sits at a wooden desk in a cozy home office, typing on a
        laptop while occasionally glancing at notes beside her. Soft natural light streams through
        a large window, casting warm shadows across the room. She pauses to take a sip from a
        ceramic mug, then continues working with focused concentration. The audio captures the
        gentle clicking of keyboard keys, the soft rustle of papers, and ambient room tone with
        occasional distant bird chirps from outside.
      conditions:
        - type: suffix
          video: "/path/to/suffix_video_1.mp4"
          # Matches temporal_boundary=8 during training: 8 * 8 = 64 frames
          num_frames: 64
    - prompt: >-
        A chef in a white uniform stands in a professional kitchen, carefully plating a gourmet
        dish with precise movements. Steam rises from freshly cooked vegetables as he arranges
        them with tweezers. The stainless steel surfaces gleam under bright overhead lights, and
        various pots simmer on the stove behind him. The audio features the sizzling of pans,
        the clinking of utensils against plates, and the ambient hum of kitchen ventilation.
      conditions:
        - type: suffix
          video: "/path/to/suffix_video_2.mp4"
          # Matches temporal_boundary=8 during training: 8 * 8 = 64 frames
          num_frames: 64
  # Negative prompt to avoid unwanted artifacts
  negative_prompt: "worst quality, inconsistent motion, blurry, jittery, distorted"
  # Output video dimensions [width, height, frames]
  # Width and height must be divisible by 32
  # Frames must satisfy: frames % 8 == 1 (e.g., 1, 9, 17, 25, 33, 41, 49, 57, 65, 73, 81, 89, ...)
  video_dims: [ 576, 576, 89 ]
  # Frame rate for generated videos
  frame_rate: 25.0
  # Random seed for reproducible validation outputs
  seed: 42
  # Number of denoising steps for validation inference
  # Higher values = better quality but slower generation
  inference_steps: 30
  # Generate validation videos every N training steps
  # Set to null to disable validation during training
  interval: 100
  # Classifier-free guidance scale
  # Higher values = stronger adherence to prompt but may introduce artifacts
  guidance_scale: 4.0
  # STG (Spatio-Temporal Guidance) parameters for improved video quality
  # STG is combined with CFG for better temporal coherence
  stg_scale: 1.0  # Recommended: 1.0 (0.0 disables STG)
  stg_blocks: [29]  # Recommended: single block 29
  stg_mode: "stg_av"  # "stg_av" perturbs both audio and video, "stg_v" video only
  # Whether to generate audio in validation samples
  # Independent of training_strategy.audio.is_generated - you can generate audio
  # in validation even when not training the audio branch
  generate_audio: true
  # Skip validation at the beginning of training (step 0)
  skip_initial_validation: false
 # -----------------------------------------------------------------------------
 # Checkpoint Configuration
 # -----------------------------------------------------------------------------
 # Controls model checkpoint saving during training.
 checkpoints:
  # Save a checkpoint every N steps
  # Set to null to disable intermediate checkpoints
  interval: 250
  # Number of most recent checkpoints to keep
  # Set to -1 to keep all checkpoints
  keep_last_n: -1
  # Precision to use when saving checkpoint weights
  # Options: "bfloat16" (default, smaller files) or "float32" (full precision)
  precision: "bfloat16"
 # -----------------------------------------------------------------------------
 # Flow Matching Configuration
 # -----------------------------------------------------------------------------
 # Parameters for the flow matching training objective.
 flow_matching:
  # Timestep sampling mode
  # "shifted_logit_normal" is recommended for LTX-2 models
  timestep_sampling_mode: "shifted_logit_normal"
  # Additional parameters for timestep sampling
  timestep_sampling_params: { }
 # -----------------------------------------------------------------------------
 # Hugging Face Hub Configuration
 # -----------------------------------------------------------------------------
 # Settings for uploading trained models to the Hugging Face Hub.
 hub:
  # Whether to push the trained model to the Hub
  push_to_hub: false
  # Repository ID on Hugging Face Hub (e.g., "username/my-lora-model")
  # Required if push_to_hub is true
  hub_model_id: null
 # -----------------------------------------------------------------------------
 # Weights & Biases Configuration
 # -----------------------------------------------------------------------------
 # Settings for experiment tracking with W&B.
 wandb:
  # Enable W&B logging
  enabled: false
  # W&B project name
  project: "ltx-2-trainer"
  # W&B username or team (null uses default account)
  entity: null
  # Tags to help organize runs
  tags: [ "ltx2", "lora", "video-suffix", "backward-extension" ]
  # Log validation media (video/audio) to W&B
  log_validation_videos: true
 # -----------------------------------------------------------------------------
 # General Configuration
 # -----------------------------------------------------------------------------
 # Global settings for the training run.
 # Random seed for reproducibility
 seed: 42
 # Directory to save outputs (checkpoints, validation videos, logs)
 output_dir: "outputs/video_suffix_lora"
@@ -1,6 +1,6 @@
 [project]
 name = "ltx-trainer"
-version = "1.1.6"
+version = "v1.1.6"
 description = "LTX-2 training, democratized."
 readme = "README.md"
 authors = [
@@ -54,7 +54,7 @@ build-backend = "hatchling.build"
 [tool.ruff]
-target-version = "1.1.6"
+target-version = "v1.1.6"
 line-length = 120
 # Restrict isort first-party detection to src/ so stray dirs (e.g. wandb/ run output)
 # next to pyproject.toml don't get classified as first-party packages. See ruff#10519.