Add SkyReels V2: Infinite-Length Film Generative Model #11518

tolgacangoz · 2025-05-07T18:58:53Z

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:
✅ SkyReelsV2Transformer3DModel: 90% WanTransformer3DModel
✅ SkyReelsV2DiffusionForcingPipeline
✅ SkyReelsV2DiffusionForcingImageToVideoPipeline: Includes FLF2V.
✅ SkyReelsV2DiffusionForcingVideoToVideoPipeline: Extends a given video.
✅ SkyReelsV2Pipeline
✅ SkyReelsV2ImageToVideoPipeline: Includes FLF2V.
✅ scripts/convert_skyreelsv2_to_diffusers.py

tolgacangoz/SkyReels-V2-Diffusers

⏳ Did you make sure to update the documentation with your changes? Did you write any new necessary tests?: We will construct these during review.

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)

Firstly, I want to congratulate you on this great work, and thanks for open-sourcing it, SkyReels Team! This PR proposes an integration of your model.

Who can review?

Anyone in the community is free to review the PR once the tests have passed. Feel free to tag members/contributors who may be interested in your PR.

@yiyixuxu @a-r-r-o-w @linoytsaban @yjp999 @Howe2018 @RoseRollZhu @pftq @Langdx @guibinchen @qiudi0127 @nitinmukesh @tin2tin @ukaprch @okaris

ukaprch · 2025-05-08T15:47:38Z

It's about time. Thanks.

tolgacangoz · 2025-05-14T15:09:16Z

Hi @yiyixuxu @a-r-r-o-w

Mid-PR questions:

The issue was labelled as "contributions-welcome" but not as "community-examples". Also, the number of stars in this model surpassed that of SkyReels-V1. Thus, I located these pipelines in src/diffusers/pipelines/skyreels_v2/. Should I move these pipelines to examples/? Should I also split this PR for each pipeline (group)?
Just like SkyReels-V1 was based on HunyuanVideo, SkyReels-V2 is based on Wan, but some differences exist. I thought of moving the differences to the parent abstraction, i.e., pipeline code, so that we can use WanTransformer3DModel for both, but it didn't seem appropriate enough to me at first. But then, if we introduce Diffusion Forcing and AutoRegressive properties into WanTransformer3DModel (as native as possible, not with the exact diff below), it seems possible to me. You can examine the current diff between transformer_wan.py and transformer_skyreels_v2.py: https://www.diffchecker.com/U72HJ6ox/ WDYT?

Since SkyReels-V2 is not a completely new architecture, should I move its pipelines into src/diffusers/pipelines/wan/ similar to HunyuanSkyreelsImageToVideoPipeline, if SkyReels-V2 is seen as an official pipeline?
I am removing TeaCache-related code because it is planned for a modular extension, right? If this PR is required to move to examples/, then no need to remove, I think.
I came across this:

diffusers/src/diffusers/models/embeddings.py

Line 1153 in 01abfc8

/ (theta ** (torch.arange(0, dim, 2, dtype=freqs_dtype, device=pos.device)[: (dim // 2)] / dim))

At first, [: (dim // 2)] confused me :S Isn't it redundant? dim was already confirmed even with assert dim % 2 == 0. Can I remove [: (dim // 2)] in a separate PR?

a-r-r-o-w · 2025-05-15T10:18:01Z

@tolgacangoz Thanks for working on this, really cool work so far!

I think we should add SkyReels models in core diffusers, so src/ is fine.

2 and 3. I think in this case, we should have separate implementation of SkyReelsV2 and Wan due to the autoregressive nature of the former. Adding any extra code in Wan might complicate it for readers. Will let @yiyixuxu comment on this though

Yeah let's remove the cache code. We'll try to write a model agnostic implementation in future once more of the cache related code is stablized after adding some of the easier methods that are not too model intrusive (such as first block cache).
You're right, it's redundant. Let's remove in a separate PR

ukaprch · 2025-05-16T15:42:18Z

FWIW, I have been successful in using the same T5 encoder for WAN 2.1 for this model just by fiddling with their pipeline:

        print('Quantize text_encoder qint8')
        class  QuantizedT5EncoderModelForCausalLM (QuantizedTransformersModel):
            auto_class = UMT5EncoderModel
            auto_class.from_config = auto_class._from_config
        text_encoder = QuantizedT5EncoderModelForCausalLM.from_pretrained(
            "./wan quantro T2V-14B-720P Diffusers/basemodel/t5encodermodel_qint8"
        ).to(dtype=dtype)
        
        pipe = Text2VideoPipeline(
            model_path=model_path,
            transformer=transformer,
            text_encoder=text_encoder,
            tokenizer=tokenizer,
            weight_dtype=dtype)

Then this: I incorporate my bitsandbytes nf4 transformer, their tokenizer and the WAN based T5 encoder:

def __init__(
    self, model_path, transformer, text_encoder, tokenizer, device: str = "cuda", weight_dtype=torch.bfloat16, use_usp=False, offload=False,
):
    self.transformer = transformer          #get_transformer(model_path, 'cpu', weight_dtype)
    vae_model_path = os.path.join(model_path, "Wan2.1_VAE.pth")
    self.vae = get_vae(vae_model_path, 'cpu', weight_dtype=torch.float32)
    if text_encoder is not None:
        self.text_encoder = text_encoder        #get_text_encoder(model_path, 'cuda', weight_dtype)
    if tokenizer is not None: 
        self.tokenizer = tokenizer

I need to add this function to the pipeline for the T5 encoder to work:

def encode(self, texts):
    ids, mask = self.tokenizer(texts, return_mask=True, add_special_tokens=True)
    ids = ids.to(self.device)
    mask = mask.to(self.device)
    context = self.text_encoder(ids, mask)
    #seq_lens = mask.gt(0).sum(dim=1).long()
    context = context.last_hidden_state * mask.unsqueeze(-1)
    return context

tolgacangoz · 2025-05-19T08:43:45Z

It seems appropriate to me. Only Diffusion Forcing pipelines are different for large models. How are the results with your setting?

tolgacangoz · 2025-05-23T11:46:22Z

Hi @yiyixuxu @a-r-r-o-w and SkyReels Team @yjp999 @pftq @Langdx @guibinchen ...

This PR will be ready for review for SkyReelsV2Transformer3DModel and SkyReelsV2DiffusionForcingPipeline soon. Other pipelines will follow quickly after initial feedback...

…mask` based on configuration flag. This change enhances flexibility in model behavior during training and inference.

…ensure consistency and correct functionality.

…sV2TimeTextImageEmbedding`.

…r cleaner code.

…itialization to directly assign the list of SkyReelsV2 components.

…ys convert query, key, and value to `torch.bfloat16`, simplifying the code and improving clarity.

…by adding VAE initialization and detailed prompt for video generation, improving clarity and usability of the documentation.

…and improve formatting in `pipeline_skyreels_v2_diffusion_forcing.py` to enhance code readability and maintainability.

…ine` from 5.0 to 6.0 to enhance video generation quality.

…definition of `SkyReelsV2DiffusionForcingPipeline` to ensure consistency and improve video generation quality.

…peline` to default to `None`.

…odel` to *ensure* correct tensor operations.

…peat_interleave` for improved efficiency in `SkyReelsV2Transformer3DModel`.

Colocates the `SkyReelsV2Timesteps` class with the SkyReelsV2 transformer model. This change moves model-specific timestep embedding logic from the general embeddings module to the transformer's own file, improving modularity and making the model more self-contained.

Replaces manual parameter iteration with the `get_parameter_dtype` helper to determine the time embedder's data type. This change improves code readability and centralizes the logic.

tolgacangoz · 2025-07-02T12:36:02Z

Or, I think they can stay as a meaning of placeholder or potential feature, because the original code was the one that I cannot produce good results with 1.3B models for FLF2V. Or, it was I who couldn't run this task properly, idk :S. Maybe it is OK with larger models. I think this PR is well-suited for its job for integration.

Edit: I opened an issue at the original repo about this. I forgot to open earlier, sry 🥲.

yiyixuxu · 2025-07-03T01:04:04Z

@tolgacangoz
are you able to refactor current FlowMatchUniPCMultistepSchedule instead of adding a new one?

Deletes the `FlowMatchUniPCMultistepScheduler` as it is no longer being used.

Removes the `FlowMatchUniPCMultistepScheduler` and integrates its functionality into the existing `UniPCMultistepScheduler`. This consolidation is achieved by using the `use_flow_sigmas=True` parameter in `UniPCMultistepScheduler`, simplifying the scheduler API and reducing code duplication. All usages, documentation, and tests are updated accordingly.

… initialization

Updates the variable name from `pipe` to `pipeline` across all SkyReels V2 documentation examples. This change improves clarity and consistency.

…ross SkyReels-V2 files

…initialization across SkyReels test files

The `generator` parameter is not used by the scheduler's `step` method within the SkyReelsV2 diffusion forcing pipelines. This change removes the unnecessary argument from the method call for code clarity and consistency.

…'s dtype in SkyReelsV2TimeTextImageEmbedding

Replaces manual parameter iteration with the `get_parameter_dtype` helper.

Adds a check to ensure the `_keep_in_fp32_modules` attribute exists on a parameter before it is accessed. This prevents a potential `AttributeError`, making the utility function more robust when used with models that do not define this attribute.

tolgacangoz · 2025-07-04T05:18:30Z

This will be my 3. pipeline contribution, yay 🥳!

yiyixuxu · 2025-07-04T06:39:26Z

src/diffusers/schedulers/scheduling_unipc_multistep.py

@@ -168,6 +168,8 @@ class UniPCMultistepScheduler(SchedulerMixin, ConfigMixin):
        use_beta_sigmas (`bool`, *optional*, defaults to `False`):
            Whether to use beta sigmas for step sizes in the noise schedule during the sampling process. Refer to [Beta
            Sampling is All You Need](https://huggingface.co/papers/2407.12173) for more information.
+        use_flow_sigmas (`bool`, *optional*, defaults to `False`):


@tolgacangoz ohh this cannot be the only change in scheduler, no?

ohh it's already in!

is the output quality match?

The outputs are qualitatively/visibly the same.

yiyixuxu

thanks!

tolgacangoz changed the title ~~Add SkyReels-V2 pipelines~~ Add SkyReels V2: Infinite-Length Film Generative Model May 16, 2025

tolgacangoz added 23 commits May 25, 2025 10:52

fix file name

00849fd

Update SkyReelsV2Transformer3DModel to conditionally apply `causal_…

8e34d89

…mask` based on configuration flag. This change enhances flexibility in model behavior during training and inference.

Merge branch 'main' into skyreels-v2

493a08c

style

a6f0d11

Fix class name casing for SkyReelsV2 components in multiple files to …

cc0660c

…ensure consistency and correct functionality.

cleaning

14d8d7a

cleansing

85a1f90

Refactor get_timestep_embedding to move modifications into `SkyReel…

5264ac9

…sV2TimeTextImageEmbedding`.

Remove unnecessary line break in get_timestep_embedding function fo…

81acfae

…r cleaner code.

Remove skyreels_v2 entry from _import_structure and update its in…

11baa00

…itialization to directly assign the list of SkyReelsV2 components.

cleansing

2906c37

Refactor attention processing in SkyReelsV2AttnProcessor2_0 to alwa…

a38eaab

…ys convert query, key, and value to `torch.bfloat16`, simplifying the code and improving clarity.

Enhance example usage in pipeline_skyreels_v2_diffusion_forcing.py …

150ea56

…by adding VAE initialization and detailed prompt for video generation, improving clarity and usability of the documentation.

Refactor import structure in __init__.py for SkyReelsV2 components …

ad7d4c4

…and improve formatting in `pipeline_skyreels_v2_diffusion_forcing.py` to enhance code readability and maintainability.

Merge branch 'main' into skyreels-v2

ed7843a

Update guidance_scale parameter in `SkyReelsV2DiffusionForcingPipel…

f1ee024

…ine` from 5.0 to 6.0 to enhance video generation quality.

Update guidance_scale parameter in example documentation and class …

421e0dc

…definition of `SkyReelsV2DiffusionForcingPipeline` to ensure consistency and improve video generation quality.

Update causal_block_size parameter in `SkyReelsV2DiffusionForcingPi…

4b688c4

…peline` to default to `None`.

up

c6b5391

Fix dtype conversion for timestep_proj in `SkyReelsV2Transformer3DM…

3bf1e4a

…odel` to *ensure* correct tensor operations.

Optimize causal mask generation by replacing repeated tensor with `re…

f48363c

…peat_interleave` for improved efficiency in `SkyReelsV2Transformer3DModel`.

style

920d956

Merge branch 'main' into skyreels-v2

cedee34

tolgacangoz and others added 5 commits July 2, 2025 14:37

Refactor parameter dtype retrieval to use utility function

ae045c7

Replaces manual parameter iteration with the `get_parameter_dtype` helper to determine the time embedder's data type. This change improves code readability and centralizes the logic.

Add comments to track the tensor shape transformations

4e66dac

Add copied froms

2326707

Merge branch 'main' into skyreels-v2

273fdd6

tolgacangoz requested a review from yiyixuxu July 2, 2025 12:36

tolgacangoz added 2 commits July 2, 2025 16:34

style

558cab2

fix-copies

8f435fe

tolgacangoz mentioned this pull request Jul 2, 2025

Propose to refactor output normalization in several transformers #11850

Draft

tolgacangoz added 15 commits July 3, 2025 16:09

up

cd2576f

Remove FlowMatchUniPCMultistepScheduler

2e24120

Deletes the `FlowMatchUniPCMultistepScheduler` as it is no longer being used.

style

766cef5

Remove text_encoder parameter from SkyReelsV2DiffusionForcingPipeline…

431cb75

… initialization

Docs: Rename pipe to pipeline in SkyReels examples

1860e25

Updates the variable name from `pipe` to `pipeline` across all SkyReels V2 documentation examples. This change improves clarity and consistency.

Fix: Rename shift parameter to flow_shift in SkyReels-V2 examples

d3a85aa

Fix: Rename shift parameter to flow_shift in example documentation ac…

d3b46ff

…ross SkyReels-V2 files

Merge branch 'main' into skyreels-v2

b2916dc

Fix: Rename shift parameter to flow_shift in UniPCMultistepScheduler …

fc3d328

…initialization across SkyReels test files

Removes unused generator argument from scheduler step

5f2de92

The `generator` parameter is not used by the scheduler's `step` method within the SkyReelsV2 diffusion forcing pipelines. This change removes the unnecessary argument from the method call for code clarity and consistency.

Fix: Update time_embedder_dtype assignment to use the first parameter…

1fbaff4

…'s dtype in SkyReelsV2TimeTextImageEmbedding

style

e8426ba

Refactor: Use get_parameter_dtype utility function

6f8d800

Replaces manual parameter iteration with the `get_parameter_dtype` helper.

Merge branch 'main' into skyreels-v2

de4089b

yiyixuxu reviewed Jul 4, 2025

View reviewed changes

yiyixuxu approved these changes Jul 4, 2025

View reviewed changes

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

Add SkyReels V2: Infinite-Length Film Generative Model #11518

Add SkyReels V2: Infinite-Length Film Generative Model #11518

tolgacangoz commented May 7, 2025 •

edited

Loading

Uh oh!

ukaprch commented May 8, 2025

Uh oh!

tolgacangoz commented May 14, 2025 •

edited

Loading

Uh oh!

a-r-r-o-w commented May 15, 2025

Uh oh!

ukaprch commented May 16, 2025

Uh oh!

tolgacangoz commented May 19, 2025 •

edited

Loading

Uh oh!

tolgacangoz commented May 23, 2025 •

edited

Loading

Uh oh!

tolgacangoz commented Jul 2, 2025 •

edited

Loading

Uh oh!

yiyixuxu commented Jul 3, 2025

Uh oh!

tolgacangoz commented Jul 4, 2025

Uh oh!

yiyixuxu Jul 4, 2025

Uh oh!

yiyixuxu Jul 4, 2025

Uh oh!

yiyixuxu Jul 4, 2025

Uh oh!

tolgacangoz Jul 4, 2025

Uh oh!

yiyixuxu left a comment

Uh oh!

Uh oh!

Add SkyReels V2: Infinite-Length Film Generative Model #11518

Are you sure you want to change the base?

Add SkyReels V2: Infinite-Length Film Generative Model #11518

Conversation

tolgacangoz commented May 7, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Original Work

T2V with Diffusion Forcing (OLD)

I2V with Diffusion Forcing (OLD)

FLF2V with Diffusion Forcing (OLD)

V2V with Diffusion Forcing (OLD)

Who can review?

Uh oh!

ukaprch commented May 8, 2025

Uh oh!

tolgacangoz commented May 14, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

a-r-r-o-w commented May 15, 2025

Uh oh!

ukaprch commented May 16, 2025

Uh oh!

tolgacangoz commented May 19, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

tolgacangoz commented May 23, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

tolgacangoz commented Jul 2, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

yiyixuxu commented Jul 3, 2025

Uh oh!

tolgacangoz commented Jul 4, 2025

Uh oh!

yiyixuxu Jul 4, 2025

Choose a reason for hiding this comment

Uh oh!

yiyixuxu Jul 4, 2025

Choose a reason for hiding this comment

Uh oh!

yiyixuxu Jul 4, 2025

Choose a reason for hiding this comment

Uh oh!

tolgacangoz Jul 4, 2025

Choose a reason for hiding this comment

Uh oh!

yiyixuxu left a comment

Choose a reason for hiding this comment

Uh oh!

Uh oh!

tolgacangoz commented May 7, 2025 •

edited

Loading

tolgacangoz commented May 14, 2025 •

edited

Loading

tolgacangoz commented May 19, 2025 •

edited

Loading

tolgacangoz commented May 23, 2025 •

edited

Loading

tolgacangoz commented Jul 2, 2025 •

edited

Loading