Add SkyReels V2: Infinite-Length Film Generative Model

[tolgacangoz]

Thanks for the opportunity to fix #11374!

Original Work

Original repo: https://github.com/SkyworkAI/SkyReels-V2
Paper: https://huggingface.co/papers/2504.13074

SkyReels V2's main contributions are summarized as follow:
• Comprehensive video captioner that understand the shot language while capturing the general description of the video, which dramatically improve the prompt adherence.
• Motion-specific preference optimization enhances motion dynamics with a semi-automatic data collection pipeline.
• Effective Diffusion-forcing adaptation enables the generation of ultra-long videos and story generation capabilities, providing a robust framework for extending temporal coherence and narrative depth.
• SkyCaptioner-V1 and SkyReels-V2 series models including diffusion-forcing, text2video, image2video, camera director and elements2video models with various sizes (1.3B, 5B, 14B) are open-sourced.

TODOs:
⏳ FlowMatchUniPCMultistepScheduler: just copy-pasted from the original repo
✅ SkyReelsV2Transformer3DModel: 90% WanTransformer3DModel
✅ SkyReelsV2DiffusionForcingPipeline

• tolgacangoz/SkyReels-V2-DF-1.3B-540P-Diffusers is ready to be forked.
• tolgacangoz/SkyReels-V2-DF-14B-720P-Diffusers is ready to be forked.
• tolgacangoz/SkyReels-V2-DF-14B-540P-Diffusers is ready to be forked.

✅ SkyReelsV2DiffusionForcingImageToVideoPipeline: Includes FLF2V.
✅ SkyReelsV2DiffusionForcingVideoToVideoPipeline: Extends a given video.
⏳ SkyReelsV2Pipeline
⏳ SkyReelsV2ImageToVideoPipeline
⏳ scripts/convert_skyreelsv2_to_diffusers.py
⬜ Did you make sure to update the documentation with your changes?
⬜ Did you write any new necessary tests?

T2V with Diffusion Forcing (OLD)

Skywork/SkyReels-V2-DF-1.3B-540P
seed 0 and num_frames 97
Original repo	diffusers integration
original_0_short.mp4	diffusers_0_short.mp4

seed 37 and num_frames 97
Original repo	diffusers integration
original_37_short.mp4	diffusers_37_short.mp4

seed 0 and num_frames 257
Original repo	diffusers integration
original_0_long.mp4	diffusers_0_long.mp4

seed 37 and num_frames 257
Original repo	diffusers integration
original_37_long.mp4	diffusers_37_long.mp4

!pip install git+https://github.com/tolgacangoz/diffusers.git@skyreels-v2 ftfy -q
import torch
from diffusers import AutoencoderKLWan, SkyReelsV2DiffusionForcingPipeline
from diffusers.utils import export_to_video

vae = AutoencoderKLWan.from_pretrained(
			"tolgacangoz/SkyReels-V2-DF-1.3B-540P-Diffusers",
			subfolder="vae",
			torch_dtype=torch.float32)
pipe = SkyReelsV2DiffusionForcingPipeline.from_pretrained(
			"tolgacangoz/SkyReels-V2-DF-1.3B-540P-Diffusers",
			vae=vae,
			torch_dtype=torch.bfloat16)
pipe = pipe.to("cuda")
pipe.transformer.set_ar_attention(causal_block_size=5)

prompt = "A cat and a dog baking a cake together in a kitchen. The cat is carefully measuring flour, while the dog is stirring the batter with a wooden spoon. The kitchen is cozy, with sunlight streaming through the window."

output = pipe(
    prompt=prompt,
    num_inference_steps=30,
    height=544,
    width=960,
    num_frames=97,
    ar_step=5,  # Controls asynchronous inference (0 for synchronous mode)
    generator=torch.Generator(device="cpu").manual_seed(0),
    overlap_history=None,  # Number of frames to overlap for smooth transitions in long videos; 17 for long
    addnoise_condition=20,  # Improves consistency in long video generation
).frames[0]
export_to_video(output, "T2V.mp4", fps=24, quality=8)

"""
You can set `ar_step=5` to enable asynchronous inference. When asynchronous inference,
`causal_block_size=5` is recommended while it is not supposed to be set for
synchronous generation. Asynchronous inference will take more steps to diffuse the
whole sequence which means it will be SLOWER than synchronous mode. In our
experiments, asynchronous inference may improve the instruction following and visual consistent performance.
"""

I2V with Diffusion Forcing (OLD)

prompt="A penguin dances."	diffusers integration
	i2v-short.mp4

#!pip uninstall diffusers -yq
#!pip install git+https://github.com/tolgacangoz/diffusers.git@skyreels-v2 ftfy -q
import torch
from diffusers import AutoencoderKLWan, SkyReelsV2DiffusionForcingImageToVideoPipeline
from diffusers.utils import export_to_video, load_image

vae = AutoencoderKLWan.from_pretrained(
			"tolgacangoz/SkyReels-V2-DF-1.3B-540P-Diffusers",
			subfolder="vae",
			torch_dtype=torch.float32)
pipe = SkyReelsV2DiffusionForcingImageToVideoPipeline.from_pretrained(
			"tolgacangoz/SkyReels-V2-DF-1.3B-540P-Diffusers",
			vae=vae,
			torch_dtype=torch.bfloat16)
pipe = pipe.to("cuda")
#pipe.transformer.set_ar_attention(causal_block_size=5)

image = load_image("Penguin from https://huggingface.co/tasks/image-to-video")
prompt = "A penguin dances."

output = pipe(
    image=image,
    prompt=prompt,
    num_inference_steps=50,
    height=544,
    width=960,
    num_frames=97,
    #ar_step=5,  # Controls asynchronous inference (0 for synchronous mode)
    generator=torch.Generator(device="cpu").manual_seed(0),
    overlap_history=None,  # Number of frames to overlap for smooth transitions in long videos; 17 for long
    addnoise_condition=20,  # Improves consistency in long video generation
).frames[0]
export_to_video(output, "I2V.mp4", fps=24, quality=8)

"""
When I set `ar_step=5` and `causal_block_size=5`, then the results seem really bad.
"""

FLF2V with Diffusion Forcing (OLD)

Now, Houston, we have a problem.
I have been unable to produce good results with this task. I tried many hyperparameter combinations with the original code.
The first frame's latent (torch.Size([1, 16, 1, 68, 120])) is overwritten onto the first of 25 frame latents of latents (torch.Size([1, 16, 25, 68, 120])). Then, the last frame's latent is concatenated, thus latents is torch.Size([1, 16, 26, 68, 120]). After the denoising process, the length of the last frame latent is discarded at the end and then decoded by the VAE. I tried not concatenating the last frame but overwriting onto the latest frame of latents and not discarding the latest frame latent at the end, but still got bad results. Here are some results:

First Frame	Last Frame
0.mp4	1.mp4
2.mp4	3.mp4
4.mp4	5.mp4
6.mp4	7.mp4

#!pip uninstall diffusers -yq
#!pip install git+https://github.com/tolgacangoz/diffusers.git@skyreels-v2 ftfy -q
import torch
from diffusers import AutoencoderKLWan, SkyReelsV2DiffusionForcingImageToVideoPipeline
from diffusers.utils import export_to_video, load_image

vae = AutoencoderKLWan.from_pretrained(
			"tolgacangoz/SkyReels-V2-DF-1.3B-540P-Diffusers",
			subfolder="vae",
			torch_dtype=torch.float32)
pipe = SkyReelsV2DiffusionForcingImageToVideoPipeline.from_pretrained(
			"tolgacangoz/SkyReels-V2-DF-1.3B-540P-Diffusers",
			vae=vae,
			torch_dtype=torch.bfloat16)
pipe = pipe.to("cuda")
#pipe.transformer.set_ar_attention(causal_block_size=5)

prompt = "CG animation style, a small blue bird takes off from the ground, flapping its wings. The bird's feathers are delicate, with a unique pattern on its chest. The background shows a blue sky with white clouds under bright sunshine. The camera follows the bird upward, capturing its flight and the vastness of the sky from a close-up, low-angle perspective."
negative_prompt = "Bright tones, overexposed, static, blurred details, subtitles, style, works, paintings, images, static, overall gray, worst quality, low quality, JPEG compression residue, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn faces, deformed, disfigured, misshapen limbs, fused fingers, still picture, messy background, three legs, many people in the background, walking backwards"
first_frame = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/flf2v_input_first_frame.png")
last_frame = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/flf2v_input_last_frame.png")

output = pipe(
    image=first_frame,
    last_image=last_frame,
    prompt=prompt,
    negative_prompt=negative_prompt,
    num_inference_steps=50,
    height=544,
    width=960,
    num_frames=97,
    #ar_step=5,  # Controls asynchronous inference (0 for synchronous mode)
    generator=torch.Generator(device="cpu").manual_seed(0),
    overlap_history=None,  # Number of frames to overlap for smooth transitions in long videos; 17 for long
    addnoise_condition=20,  # Improves consistency in long video generation
).frames[0]
export_to_video(output, "FLF2V.mp4", fps=24, quality=8)

V2V with Diffusion Forcing (OLD)

This pipeline extends a given video.

Input Video	diffusers integration
video1.mp4	v2v.mp4

#!pip uninstall diffusers -yq
#!pip install git+https://github.com/tolgacangoz/diffusers.git@skyreels-v2 ftfy -q
import torch
from diffusers import AutoencoderKLWan, SkyReelsV2DiffusionForcingVideoToVideoPipeline
from diffusers.utils import export_to_video, load_video

vae = AutoencoderKLWan.from_pretrained(
			"tolgacangoz/SkyReels-V2-DF-1.3B-540P-Diffusers",
			subfolder="vae",
			torch_dtype=torch.float32)
pipe = SkyReelsV2DiffusionForcingVideoToVideoPipeline.from_pretrained(
			"tolgacangoz/SkyReels-V2-DF-1.3B-540P-Diffusers",
			vae=vae,
			torch_dtype=torch.bfloat16)
pipe = pipe.to("cuda")
#pipe.transformer.set_ar_attention(causal_block_size=5)

prompt = "CG animation style, a small blue bird flaps its wings. The bird's feathers are delicate, with a unique pattern on its chest. The background shows a blue sky with white clouds under bright sunshine. The camera follows the bird upward, capturing its continuing flight and the vastness of the sky from a close-up, low-angle perspective."
negative_prompt = "Bright tones, overexposed, static, blurred details, subtitles, style, works, paintings, images, static, overall gray, worst quality, low quality, JPEG compression residue, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn faces, deformed, disfigured, misshapen limbs, fused fingers, still picture, messy background, three legs, many people in the background, walking backwards"
video = load_video("Input video.mp4")

output = pipe(
    video=video,
    prompt=prompt,
    num_inference_steps=50,
    height=544,
    width=960,
    num_frames=120,
    base_num_frames=97,
    ar_step=0,  # Controls asynchronous inference (0 for synchronous mode)
    generator=torch.Generator(device="cpu").manual_seed(0),
    overlap_history=17,  # Number of frames to overlap for smooth transitions in long videos
    addnoise_condition=20,  # Improves consistency in long video generation
).frames[0]
export_to_video(output, "V2V.mp4", fps=24, quality=8)

[ukaprch]

It's about time. Thanks.

[a-r-r-o-w]

@tolgacangoz Awesome work so far, just checking in on the progress. Still trying to fully wrap my head around diffusion forcing and trying to visually verify that diffusers version code matches original. As a sanity check, do we know why the output of T2V from the original code vs diffusers is different? Typically, we try to ensure that given the same starting embeddings, seed and other starting conditions, the output from different implementations matches numerically with threshold < 1e-3. I will try to help with debugging and testing 🤗

[tolgacangoz]

The original code had a default negative prompt (which I wasn't aware of at the time); this might have been the reason; or something about timestep processing. I will try to make it as deterministically matchable as possible.

[tolgacangoz]

Today I mostly followed by reading the code. But tomorrow I will be more systematic: I will go through the inputs and outputs of each module step by step.

[tolgacangoz]

I have finally discovered the reasons for the discrepancy and will share them tomorrow 🥳!