[HunyuanVideo1.5] support step-distilled

[yiyixuxu]

adding support for https://huggingface.co/tencent/HunyuanVideo-1.5/tree/main/transformer/480p_i2v_step_distilled

import torch

dtype = torch.bfloat16
device = "cuda:0"
from diffusers import HunyuanVideo15ImageToVideoPipeline, attention_backend
from diffusers.utils import export_to_video, load_image

pipe = HunyuanVideo15ImageToVideoPipeline.from_pretrained("hunyuanvideo-community/HunyuanVideo-1.5-Diffusers-480p_i2v_step_distilled", torch_dtype=dtype)
pipe.enable_model_cpu_offload()
pipe.vae.enable_tiling()

generator = torch.Generator(device=device).manual_seed(1)
image = load_image("https://huggingface.co/datasets/YiYiXu/testing-images/resolve/main/wan_i2v_input.JPG")
prompt="Summer beach vacation style, a white cat wearing sunglasses sits on a surfboard. The fluffy-furred feline gazes directly at the camera with a relaxed expression. Blurred beach scenery forms the background featuring crystal-clear waters, distant green hills, and a blue sky dotted with white clouds. The cat assumes a naturally relaxed posture, as if savoring the sea breeze and warm sunlight. A close-up shot highlights the feline's intricate details and the refreshing atmosphere of the seaside."
with attention_backend("flash_varlen"): # or `"flash_varlen_hub"
    video = pipe(
        prompt=prompt,
        image=image,
        generator=generator,
        num_frames=121,
        num_inference_steps=12,
    ).frames[0]
export_to_video(video, "yiyi_test_7_1_output.mp4", fps=24)

[HuggingFaceDocBuilderDev]

The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update.

[sayakpaul]

Very lean!

[sayakpaul]

Maybe slightly better?

Suggested change

	if config.use_meanflow:
	if config is not None and getattr(config, "use_meanflow", False):

[sayakpaul]

(nit): Maybe time_proj_meanflow and timestep_embedder_meanflow are better names?