[wan2.2] fix vae patches

[yiyixuxu]

fix #12034

import torch
import numpy as np
from diffusers import WanImageToVideoPipeline, AutoencoderKLWan, ModularPipeline
from diffusers.utils import export_to_video


model_id = "Wan-AI/Wan2.2-TI2V-5B-Diffusers"
dtype = torch.bfloat16
device = "cuda:1"

vae = AutoencoderKLWan.from_pretrained(model_id, subfolder="vae", torch_dtype=torch.float32)
pipe = WanImageToVideoPipeline.from_pretrained(model_id, vae=vae, torch_dtype=dtype)
pipe.to(device)

# # use default wan image processor to resize and crop the image
image_processor = ModularPipeline.from_pretrained("YiYiXu/WanImageProcessor", trust_remote_code=True)
image = image_processor(
    image="https://cloud.inference.sh/u/4mg21r6ta37mpaz6ktzwtt8krr/01k1g7k73eebnrmzmc6h0bghq6.png",
    max_area=1280*704, output="processed_image")

height, width = image.height, image.width
print(f"height: {height}, width: {width}")
num_frames = 49
num_inference_steps =38
guidance_scale = 5.0

prompt = "morpheus from the matrix offering the choice, include morpheus, on one hand it says \"local\" on the other it says \"cloud\""

negative_prompt = "色调艳丽，过曝，静态，细节模糊不清，字幕，风格，作品，画作，画面，静止，整体发灰，最差质量，低质量，JPEG压缩残留，丑陋的，残缺的，多余的手指，画得不好的手部，画得不好的脸部，畸形的，毁容的，形态畸形的肢体，手指融合，静止不动的画面，杂乱的背景，三条腿，背景人很多，倒着走"
generator = torch.Generator(device=device).manual_seed(42)
output = pipe(
    image=image,
    prompt=prompt,
    negative_prompt=negative_prompt,
    height=height,
    width=width,
    num_frames=num_frames,
    guidance_scale=guidance_scale,
    num_inference_steps=num_inference_steps,
    generator=generator,
    #latents=latents,
).frames[0]
export_to_video(output, "yiyi_test_6_2_output.mp4", fps=24)

yiyi_test_6_2_output.mp4

[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.