keyframe_interpolation.py

import logging

import torch

from ltx_core.allocator_trim_strategy import AllocatorTrimStrategy
from ltx_core.components.guiders import (
    MultiModalGuiderFactory,
    MultiModalGuiderParams,
    create_multimodal_guider_factory,
)
from ltx_core.components.noisers import GaussianNoiser
from ltx_core.components.schedulers import LTX2Scheduler
from ltx_core.loader import LoraPathStrengthAndSDOps
from ltx_core.loader.registry import Registry
from ltx_core.model.transformer.compiling import CompilationConfig
from ltx_core.model.video_vae import AUTO_TILING, AutoTiling, TilingConfig, get_video_chunks_number
from ltx_core.model.video_vae.transformer import DiffVAEMode
from ltx_core.quantization import QuantizationPolicy
from ltx_core.types import VideoPixelShape
from ltx_pipelines.utils.args import (
    ImageConditioningInput,
    default_2_stage_arg_parser,
    resolve_cli_params,
)
from ltx_pipelines.utils.blocks import (
    AudioDecoder,
    DiffusionStage,
    ImageConditioner,
    PromptEncoder,
    VideoDecoder,
    VideoUpsampler,
)
from ltx_pipelines.utils.constants import (
    STAGE_2_DISTILLED_SIGMAS,
)
from ltx_pipelines.utils.denoisers import FactoryGuidedDenoiser, SimpleDenoiser
from ltx_pipelines.utils.helpers import (
    assert_resolution,
    ensure_tiling_config,
    get_device,
    image_conditionings_by_adding_guiding_latent,
    tiling_scale_factors_for_vae,
)
from ltx_pipelines.utils.media_io import (
    HDRColorSpace,
    encode_video,
    resolve_hdr_color_space,
    vae_dtype_for_hdr,
)
from ltx_pipelines.utils.model_paths import ModelPaths
from ltx_pipelines.utils.types import ModalitySpec, OffloadMode, PipelineOutput


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__(  # noqa: PLR0913
        self,
        model_paths: ModelPaths,
        distilled_lora: list[LoraPathStrengthAndSDOps],
        spatial_upsampler_path: str,
        loras: list[LoraPathStrengthAndSDOps],
        device: torch.device | None = None,
        quantization: QuantizationPolicy | None = None,
        registry: Registry | None = None,
        compilation_config: CompilationConfig | None = None,
        offload_mode: OffloadMode = OffloadMode.NONE,
        alloc_trim_strategy: AllocatorTrimStrategy = AllocatorTrimStrategy.TRIM,
        prompt_enhancer_gemma_root: str | None = None,
        diffvae_optimization: DiffVAEMode = DiffVAEMode.CHUNKED_EAGER,
    ):
        self.device = device or get_device()
        self.dtype = torch.bfloat16
        self._scheduler = LTX2Scheduler()

        self.prompt_encoder = PromptEncoder(
            model_paths,
            self.dtype,
            self.device,
            registry=registry,
            offload_mode=offload_mode,
            alloc_trim_strategy=alloc_trim_strategy,
            prompt_enhancer_gemma_root=prompt_enhancer_gemma_root,
        )
        self.image_conditioner = ImageConditioner(
            model_paths.video_vae(),
            self.dtype,
            self.device,
            registry=registry,
            alloc_trim_strategy=alloc_trim_strategy,
        )
        self.stage_1 = DiffusionStage.from_checkpoint(
            model_paths.transformer(),
            self.dtype,
            self.device,
            loras=tuple(loras),
            quantization=quantization,
            registry=registry,
            compilation_config=compilation_config,
            offload_mode=offload_mode,
            alloc_trim_strategy=alloc_trim_strategy,
        )
        stage_2_loras = (*tuple(loras), *tuple(distilled_lora))
        self.stage_2 = DiffusionStage.from_checkpoint(
            model_paths.transformer(),
            self.dtype,
            self.device,
            loras=stage_2_loras,
            quantization=quantization,
            registry=registry,
            compilation_config=compilation_config,
            offload_mode=offload_mode,
            alloc_trim_strategy=alloc_trim_strategy,
        )
        self.upsampler = VideoUpsampler(
            model_paths.video_vae(),
            spatial_upsampler_path,
            self.dtype,
            self.device,
            registry=registry,
            alloc_trim_strategy=alloc_trim_strategy,
        )
        self.video_decoder = VideoDecoder(
            model_paths.video_vae(),
            self.dtype,
            self.device,
            registry=registry,
            alloc_trim_strategy=alloc_trim_strategy,
            diffvae_optimization=diffvae_optimization,
        )
        self.audio_decoder = AudioDecoder(
            model_paths.audio_vae(),
            self.dtype,
            self.device,
            registry=registry,
            alloc_trim_strategy=alloc_trim_strategy,
        )

    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],
        vae_dtype: torch.dtype | None = None,
        tiling_config: TilingConfig | AutoTiling | None = AUTO_TILING,
        enhance_prompt: bool = False,
        enhance_static_cache: bool = False,
        max_batch_size: int = 1,
        stage_1_sigmas: torch.Tensor | None = None,
        stage_2_sigmas: torch.Tensor = STAGE_2_DISTILLED_SIGMAS,
        color_space: HDRColorSpace | None = None,
    ) -> PipelineOutput:
        images = self.image_conditioner.resolve_crf(images)
        assert_resolution(height=height, width=width, is_two_stage=True)

        generator = torch.Generator(device=self.device).manual_seed(seed)
        noiser = GaussianNoiser(generator=generator)
        dtype = torch.bfloat16
        if vae_dtype is None:
            vae_dtype = dtype

        ctx_p, ctx_n = self.prompt_encoder(
            [prompt, negative_prompt],
            enhance_first_prompt=enhance_prompt,
            enhance_static_cache=enhance_static_cache,
            enhance_prompt_image=images[0][0] if len(images) > 0 else None,
        )
        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

        scale_factors = tiling_scale_factors_for_vae(self.video_decoder.checkpoint_path)
        tiling_config = ensure_tiling_config(
            tiling_config,
            scale_factors=scale_factors,
            vae_checkpoint_path=self.video_decoder.checkpoint_path,
            video_shape=VideoPixelShape(batch=1, frames=num_frames, height=height, width=width, fps=frame_rate),
            diffvae_optimization=self.video_decoder.diffvae_optimization,
            device=self.device,
        )

        # Stage 1: Initial low resolution video generation.
        sigmas = (
            stage_1_sigmas if stage_1_sigmas is not None else self._scheduler.execute(steps=num_inference_steps)
        ).to(dtype=torch.float32, device=self.device)

        stage_1_output_shape = VideoPixelShape(
            batch=1,
            frames=num_frames,
            width=width // 2,
            height=height // 2,
            fps=frame_rate,
        )
        stage_1_conditionings = self.image_conditioner(
            lambda enc: image_conditionings_by_adding_guiding_latent(
                images=images,
                height=stage_1_output_shape.height,
                width=stage_1_output_shape.width,
                video_encoder=enc,
                dtype=dtype,
                device=self.device,
                color_space=color_space,
            )
        )

        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,
        )

        video_state, audio_state = self.stage_1(
            denoiser=FactoryGuidedDenoiser(
                v_context=v_context_p,
                a_context=a_context_p,
                video_guider_factory=video_guider_factory,
                audio_guider_factory=audio_guider_factory,
            ),
            sigmas=sigmas,
            noiser=noiser,
            width=stage_1_output_shape.width,
            height=stage_1_output_shape.height,
            frames=num_frames,
            fps=frame_rate,
            video=ModalitySpec(
                context=v_context_p,
                conditionings=stage_1_conditionings,
            ),
            audio=ModalitySpec(
                context=a_context_p,
            ),
            max_batch_size=max_batch_size,
        )

        # Stage 2: Upsample and refine the video at higher resolution with distilled LORA.
        upscaled_video_latent = self.upsampler(video_state.latent[:1])

        stage_2_sigmas = stage_2_sigmas.to(dtype=torch.float32, device=self.device)
        stage_2_output_shape = VideoPixelShape(batch=1, frames=num_frames, width=width, height=height, fps=frame_rate)
        stage_2_conditionings = self.image_conditioner(
            lambda enc: image_conditionings_by_adding_guiding_latent(
                images=images,
                height=stage_2_output_shape.height,
                width=stage_2_output_shape.width,
                video_encoder=enc,
                dtype=dtype,
                device=self.device,
                color_space=color_space,
            )
        )

        video_state, audio_state = self.stage_2(
            denoiser=SimpleDenoiser(v_context_p, a_context_p),
            sigmas=stage_2_sigmas,
            noiser=noiser,
            width=width,
            height=height,
            frames=num_frames,
            fps=frame_rate,
            video=ModalitySpec(
                context=v_context_p,
                conditionings=stage_2_conditionings,
                noise_scale=stage_2_sigmas[0].item(),
                initial_latent=upscaled_video_latent,
            ),
            audio=ModalitySpec(
                context=a_context_p,
                noise_scale=stage_2_sigmas[0].item(),
                initial_latent=audio_state.latent,
            ),
        )

        decoded_video = self.video_decoder(video_state.latent, tiling_config, generator, dtype=vae_dtype)
        decoded_audio = self.audio_decoder(audio_state.latent)
        return PipelineOutput(decoded_video, decoded_audio, num_frames, tiling_config, None, video_state.latent)


@torch.inference_mode()
def main() -> None:
    logging.basicConfig(level=logging.INFO)
    params = resolve_cli_params()
    parser = default_2_stage_arg_parser(params=params)
    args = parser.parse_args()
    pipeline = KeyframeInterpolationPipeline(
        model_paths=args.model_paths,
        distilled_lora=args.distilled_lora,
        spatial_upsampler_path=args.spatial_upsampler_path,
        loras=tuple(args.lora) if args.lora else (),
        quantization=args.quantization,
        compilation_config=args.compile,
        offload_mode=args.offload_mode,
        prompt_enhancer_gemma_root=args.prompt_enhancer_gemma_root,
        diffvae_optimization=args.diffvae_optimization,
    )
    hdr = resolve_hdr_color_space(images=args.images, hdr=args.hdr)
    vae_dtype = vae_dtype_for_hdr(hdr, torch.bfloat16)
    result = 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,
        vae_dtype=vae_dtype,
        color_space=hdr,
        enhance_prompt=args.enhance_prompt,
        enhance_static_cache=args.enhance_static_cache,
        tiling_config=AUTO_TILING,
        max_batch_size=args.max_batch_size,
    )
    encode_video(
        video=result.video,
        fps=args.frame_rate,
        audio=result.audio,
        output_path=args.output_path,
        video_chunks_number=get_video_chunks_number(result.num_frames, result.tiling_config),
        color_space=hdr,
    )


if __name__ == "__main__":
    main()