sync-bot
296 lines
11 KiB
Python
296 lines
11 KiB
Python
import logging
|
|
from collections.abc import Iterator
|
|
|
|
import torch
|
|
|
|
from ltx_core.components.diffusion_steps import EulerDiffusionStep
|
|
from ltx_core.components.guiders import (
|
|
MultiModalGuiderFactory,
|
|
MultiModalGuiderParams,
|
|
create_multimodal_guider_factory,
|
|
)
|
|
from ltx_core.components.noisers import GaussianNoiser
|
|
from ltx_core.components.protocols import DiffusionStepProtocol
|
|
from ltx_core.components.schedulers import LTX2Scheduler
|
|
from ltx_core.loader import LoraPathStrengthAndSDOps
|
|
from ltx_core.model.audio_vae import decode_audio as vae_decode_audio
|
|
from ltx_core.model.upsampler import upsample_video
|
|
from ltx_core.model.video_vae import TilingConfig, get_video_chunks_number
|
|
from ltx_core.model.video_vae import decode_video as vae_decode_video
|
|
from ltx_core.quantization import QuantizationPolicy
|
|
from ltx_core.types import Audio, LatentState, VideoPixelShape
|
|
from ltx_pipelines.utils import ModelLedger
|
|
from ltx_pipelines.utils.args import ImageConditioningInput, default_2_stage_arg_parser, detect_checkpoint_path
|
|
from ltx_pipelines.utils.constants import STAGE_2_DISTILLED_SIGMA_VALUES, detect_params
|
|
from ltx_pipelines.utils.helpers import (
|
|
assert_resolution,
|
|
cleanup_memory,
|
|
denoise_audio_video,
|
|
encode_prompts,
|
|
get_device,
|
|
image_conditionings_by_adding_guiding_latent,
|
|
multi_modal_guider_factory_denoising_func,
|
|
simple_denoising_func,
|
|
)
|
|
from ltx_pipelines.utils.media_io import encode_video
|
|
from ltx_pipelines.utils.samplers import euler_denoising_loop
|
|
from ltx_pipelines.utils.types import PipelineComponents
|
|
|
|
device = get_device()
|
|
|
|
|
|
class KeyframeInterpolationPipeline:
|
|
"""
|
|
Keyframe-based Two-stage video interpolation pipeline.
|
|
Interpolates between keyframes to generate a video with smoother transitions.
|
|
Stage 1 generates video at half of the target resolution, then Stage 2 upsamples
|
|
by 2x and refines with additional denoising steps for higher quality output.
|
|
Stage 1 uses full model while Stage 2 uses distilled LORA for efficiency,
|
|
as the upsampled video already has good quality and just needs refinement.
|
|
"""
|
|
|
|
def __init__(
|
|
self,
|
|
checkpoint_path: str,
|
|
distilled_lora: list[LoraPathStrengthAndSDOps],
|
|
spatial_upsampler_path: str,
|
|
gemma_root: str,
|
|
loras: list[LoraPathStrengthAndSDOps],
|
|
device: torch.device = device,
|
|
quantization: QuantizationPolicy | None = None,
|
|
):
|
|
self.device = device
|
|
self.dtype = torch.bfloat16
|
|
self.stage_1_model_ledger = ModelLedger(
|
|
dtype=self.dtype,
|
|
device=device,
|
|
checkpoint_path=checkpoint_path,
|
|
spatial_upsampler_path=spatial_upsampler_path,
|
|
gemma_root_path=gemma_root,
|
|
loras=loras,
|
|
quantization=quantization,
|
|
)
|
|
self.stage_2_model_ledger = self.stage_1_model_ledger.with_additional_loras(
|
|
loras=distilled_lora,
|
|
)
|
|
self.pipeline_components = PipelineComponents(
|
|
dtype=self.dtype,
|
|
device=device,
|
|
)
|
|
|
|
def __call__( # noqa: PLR0913
|
|
self,
|
|
prompt: str,
|
|
negative_prompt: str,
|
|
seed: int,
|
|
height: int,
|
|
width: int,
|
|
num_frames: int,
|
|
frame_rate: float,
|
|
num_inference_steps: int,
|
|
video_guider_params: MultiModalGuiderParams | MultiModalGuiderFactory,
|
|
audio_guider_params: MultiModalGuiderParams | MultiModalGuiderFactory,
|
|
images: list[ImageConditioningInput],
|
|
tiling_config: TilingConfig | None = None,
|
|
enhance_prompt: bool = False,
|
|
) -> tuple[Iterator[torch.Tensor], Audio]:
|
|
assert_resolution(height=height, width=width, is_two_stage=True)
|
|
|
|
generator = torch.Generator(device=self.device).manual_seed(seed)
|
|
noiser = GaussianNoiser(generator=generator)
|
|
stepper = EulerDiffusionStep()
|
|
dtype = torch.bfloat16
|
|
|
|
ctx_p, ctx_n = encode_prompts(
|
|
[prompt, negative_prompt],
|
|
self.stage_1_model_ledger,
|
|
enhance_first_prompt=enhance_prompt,
|
|
enhance_prompt_image=images[0][0] if len(images) > 0 else None,
|
|
enhance_prompt_seed=seed,
|
|
)
|
|
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
|
|
|
|
# Stage 1: Initial low resolution video generation.
|
|
video_encoder = self.stage_1_model_ledger.video_encoder()
|
|
transformer = self.stage_1_model_ledger.transformer()
|
|
sigmas = LTX2Scheduler().execute(steps=num_inference_steps).to(dtype=torch.float32, device=self.device)
|
|
|
|
def first_stage_denoising_loop(
|
|
sigmas: torch.Tensor, video_state: LatentState, audio_state: LatentState, stepper: DiffusionStepProtocol
|
|
) -> tuple[LatentState, LatentState]:
|
|
return euler_denoising_loop(
|
|
sigmas=sigmas,
|
|
video_state=video_state,
|
|
audio_state=audio_state,
|
|
stepper=stepper,
|
|
denoise_fn=multi_modal_guider_factory_denoising_func(
|
|
video_guider_factory=create_multimodal_guider_factory(
|
|
params=video_guider_params,
|
|
negative_context=v_context_n,
|
|
),
|
|
audio_guider_factory=create_multimodal_guider_factory(
|
|
params=audio_guider_params,
|
|
negative_context=a_context_n,
|
|
),
|
|
v_context=v_context_p,
|
|
a_context=a_context_p,
|
|
transformer=transformer, # noqa: F821
|
|
),
|
|
)
|
|
|
|
stage_1_output_shape = VideoPixelShape(
|
|
batch=1,
|
|
frames=num_frames,
|
|
width=width // 2,
|
|
height=height // 2,
|
|
fps=frame_rate,
|
|
)
|
|
stage_1_conditionings = image_conditionings_by_adding_guiding_latent(
|
|
images=images,
|
|
height=stage_1_output_shape.height,
|
|
width=stage_1_output_shape.width,
|
|
video_encoder=video_encoder,
|
|
dtype=dtype,
|
|
device=self.device,
|
|
)
|
|
video_state, audio_state = denoise_audio_video(
|
|
output_shape=stage_1_output_shape,
|
|
conditionings=stage_1_conditionings,
|
|
noiser=noiser,
|
|
sigmas=sigmas,
|
|
stepper=stepper,
|
|
denoising_loop_fn=first_stage_denoising_loop,
|
|
components=self.pipeline_components,
|
|
dtype=dtype,
|
|
device=self.device,
|
|
)
|
|
|
|
torch.cuda.synchronize()
|
|
del transformer
|
|
cleanup_memory()
|
|
|
|
# Stage 2: Upsample and refine the video at higher resolution with distilled LORA.
|
|
upscaled_video_latent = upsample_video(
|
|
latent=video_state.latent[:1],
|
|
video_encoder=video_encoder,
|
|
upsampler=self.stage_2_model_ledger.spatial_upsampler(),
|
|
)
|
|
|
|
torch.cuda.synchronize()
|
|
cleanup_memory()
|
|
|
|
transformer = self.stage_2_model_ledger.transformer()
|
|
distilled_sigmas = torch.Tensor(STAGE_2_DISTILLED_SIGMA_VALUES).to(self.device)
|
|
|
|
def second_stage_denoising_loop(
|
|
sigmas: torch.Tensor, video_state: LatentState, audio_state: LatentState, stepper: DiffusionStepProtocol
|
|
) -> tuple[LatentState, LatentState]:
|
|
return euler_denoising_loop(
|
|
sigmas=sigmas,
|
|
video_state=video_state,
|
|
audio_state=audio_state,
|
|
stepper=stepper,
|
|
denoise_fn=simple_denoising_func(
|
|
video_context=v_context_p,
|
|
audio_context=a_context_p,
|
|
transformer=transformer, # noqa: F821
|
|
),
|
|
)
|
|
|
|
stage_2_output_shape = VideoPixelShape(batch=1, frames=num_frames, width=width, height=height, fps=frame_rate)
|
|
stage_2_conditionings = image_conditionings_by_adding_guiding_latent(
|
|
images=images,
|
|
height=stage_2_output_shape.height,
|
|
width=stage_2_output_shape.width,
|
|
video_encoder=video_encoder,
|
|
dtype=dtype,
|
|
device=self.device,
|
|
)
|
|
video_state, audio_state = denoise_audio_video(
|
|
output_shape=stage_2_output_shape,
|
|
conditionings=stage_2_conditionings,
|
|
noiser=noiser,
|
|
sigmas=distilled_sigmas,
|
|
stepper=stepper,
|
|
denoising_loop_fn=second_stage_denoising_loop,
|
|
components=self.pipeline_components,
|
|
dtype=dtype,
|
|
device=self.device,
|
|
noise_scale=distilled_sigmas[0],
|
|
initial_video_latent=upscaled_video_latent,
|
|
initial_audio_latent=audio_state.latent,
|
|
)
|
|
|
|
torch.cuda.synchronize()
|
|
del transformer
|
|
del video_encoder
|
|
cleanup_memory()
|
|
|
|
decoded_video = vae_decode_video(
|
|
video_state.latent, self.stage_2_model_ledger.video_decoder(), tiling_config, generator
|
|
)
|
|
decoded_audio = vae_decode_audio(
|
|
audio_state.latent, self.stage_2_model_ledger.audio_decoder(), self.stage_2_model_ledger.vocoder()
|
|
)
|
|
return decoded_video, decoded_audio
|
|
|
|
|
|
@torch.inference_mode()
|
|
def main() -> None:
|
|
logging.getLogger().setLevel(logging.INFO)
|
|
checkpoint_path = detect_checkpoint_path()
|
|
params = detect_params(checkpoint_path)
|
|
parser = default_2_stage_arg_parser(params=params)
|
|
args = parser.parse_args()
|
|
pipeline = KeyframeInterpolationPipeline(
|
|
checkpoint_path=args.checkpoint_path,
|
|
distilled_lora=args.distilled_lora,
|
|
spatial_upsampler_path=args.spatial_upsampler_path,
|
|
gemma_root=args.gemma_root,
|
|
loras=tuple(args.lora) if args.lora else (),
|
|
quantization=args.quantization,
|
|
)
|
|
tiling_config = TilingConfig.default()
|
|
video_chunks_number = get_video_chunks_number(args.num_frames, tiling_config)
|
|
video, audio = pipeline(
|
|
prompt=args.prompt,
|
|
negative_prompt=args.negative_prompt,
|
|
seed=args.seed,
|
|
height=args.height,
|
|
width=args.width,
|
|
num_frames=args.num_frames,
|
|
frame_rate=args.frame_rate,
|
|
num_inference_steps=args.num_inference_steps,
|
|
video_guider_params=MultiModalGuiderParams(
|
|
cfg_scale=args.video_cfg_guidance_scale,
|
|
stg_scale=args.video_stg_guidance_scale,
|
|
rescale_scale=args.video_rescale_scale,
|
|
modality_scale=args.a2v_guidance_scale,
|
|
skip_step=args.video_skip_step,
|
|
stg_blocks=args.video_stg_blocks,
|
|
),
|
|
audio_guider_params=MultiModalGuiderParams(
|
|
cfg_scale=args.audio_cfg_guidance_scale,
|
|
stg_scale=args.audio_stg_guidance_scale,
|
|
rescale_scale=args.audio_rescale_scale,
|
|
modality_scale=args.v2a_guidance_scale,
|
|
skip_step=args.audio_skip_step,
|
|
stg_blocks=args.audio_stg_blocks,
|
|
),
|
|
images=args.images,
|
|
tiling_config=tiling_config,
|
|
)
|
|
|
|
encode_video(
|
|
video=video,
|
|
fps=args.frame_rate,
|
|
audio=audio,
|
|
output_path=args.output_path,
|
|
video_chunks_number=video_chunks_number,
|
|
)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
main()
|