indigo/LTX-2
1
0
Fork 0
Code Issues Pull Requests 1 Actions Packages Projects Releases Wiki Activity

Automated PR - 2026-04-23

Browse Source
This commit is contained in:
github-actions[bot]
2026-04-23 12:43:54 +00:00
parent a2c3f24078
commit b604d3fab3
49 changed files with 2664 additions and 568 deletions
Download Patch File Download Diff File Expand all files Collapse all files
packages/ltx-pipelines/src/ltx_pipelines/keyframe_interpolation.py
+13 -8
View File
@@ -15,7 +15,11 @@ from ltx_core.loader.registry import Registry
from ltx_core.model.video_vae import TilingConfig, get_video_chunks_number
from ltx_core.quantization import QuantizationPolicy
from ltx_core.types import Audio, VideoPixelShape
from ltx_pipelines.utils.args import ImageConditioningInput, default_2_stage_arg_parser, detect_checkpoint_path
from ltx_pipelines.utils.args import (
ImageConditioningInput,
default_2_stage_arg_parser,
detect_checkpoint_path,
)
from ltx_pipelines.utils.blocks import (
AudioDecoder,
DiffusionStage,
@@ -35,7 +39,7 @@ from ltx_pipelines.utils.helpers import (
image_conditionings_by_adding_guiding_latent,
)
from ltx_pipelines.utils.media_io import encode_video
from ltx_pipelines.utils.types import ModalitySpec
from ltx_pipelines.utils.types import ModalitySpec, OffloadMode
class KeyframeInterpolationPipeline:
@@ -59,12 +63,15 @@ class KeyframeInterpolationPipeline:
quantization: QuantizationPolicy | None = None,
registry: Registry | None = None,
torch_compile: bool = False,
offload_mode: OffloadMode = OffloadMode.NONE,
):
self.device = device or get_device()
self.dtype = torch.bfloat16
self._scheduler = LTX2Scheduler()
self.prompt_encoder = PromptEncoder(checkpoint_path, gemma_root, self.dtype, self.device, registry=registry)
self.prompt_encoder = PromptEncoder(
checkpoint_path, gemma_root, self.dtype, self.device, registry=registry, offload_mode=offload_mode
)
self.image_conditioner = ImageConditioner(checkpoint_path, self.dtype, self.device, registry=registry)
self.stage_1 = DiffusionStage(
checkpoint_path,
@@ -74,6 +81,7 @@ class KeyframeInterpolationPipeline:
quantization=quantization,
registry=registry,
torch_compile=torch_compile,
offload_mode=offload_mode,
)
stage_2_loras = (*tuple(loras), *tuple(distilled_lora))
self.stage_2 = DiffusionStage(
@@ -84,6 +92,7 @@ class KeyframeInterpolationPipeline:
quantization=quantization,
registry=registry,
torch_compile=torch_compile,
offload_mode=offload_mode,
)
self.upsampler = VideoUpsampler(
checkpoint_path, spatial_upsampler_path, self.dtype, self.device, registry=registry
@@ -106,7 +115,6 @@ class KeyframeInterpolationPipeline:
images: list[ImageConditioningInput],
tiling_config: TilingConfig | None = None,
enhance_prompt: bool = False,
streaming_prefetch_count: int | None = None,
max_batch_size: int = 1,
stage_1_sigmas: torch.Tensor | None = None,
stage_2_sigmas: torch.Tensor = STAGE_2_DISTILLED_SIGMAS,
@@ -122,7 +130,6 @@ class KeyframeInterpolationPipeline:
enhance_first_prompt=enhance_prompt,
enhance_prompt_image=images[0][0] if len(images) > 0 else None,
enhance_prompt_seed=seed,
streaming_prefetch_count=streaming_prefetch_count,
)
v_context_p, a_context_p = ctx_p.video_encoding, ctx_p.audio_encoding
v_context_n, a_context_n = ctx_n.video_encoding, ctx_n.audio_encoding
@@ -179,7 +186,6 @@ class KeyframeInterpolationPipeline:
audio=ModalitySpec(
context=a_context_p,
),
streaming_prefetch_count=streaming_prefetch_count,
max_batch_size=max_batch_size,
)
@@ -218,7 +224,6 @@ class KeyframeInterpolationPipeline:
noise_scale=stage_2_sigmas[0].item(),
initial_latent=audio_state.latent,
),
streaming_prefetch_count=streaming_prefetch_count,
)
decoded_video = self.video_decoder(video_state.latent, tiling_config, generator)
@@ -241,6 +246,7 @@ def main() -> None:
loras=tuple(args.lora) if args.lora else (),
quantization=args.quantization,
torch_compile=args.compile,
offload_mode=args.offload_mode,
)
tiling_config = TilingConfig.default()
video_chunks_number = get_video_chunks_number(args.num_frames, tiling_config)
@@ -271,7 +277,6 @@ def main() -> None:
),
images=args.images,
tiling_config=tiling_config,
streaming_prefetch_count=args.streaming_prefetch_count,
max_batch_size=args.max_batch_size,
)