support Wan-FLF2V

[yiyixuxu]

will merge once we upload our checkpoint to an official repo :)

import numpy as np
import torch
import torchvision.transforms.functional as TF
from diffusers import AutoencoderKLWan, WanImageToVideoPipeline
from diffusers.utils import export_to_video, load_image
from transformers import CLIPVisionModel

# model_id = "Wan-AI/Wan2.1-FLF2V-14B-720P-diffusers"
# using this for testing for now, will move to official repo
model_id = "YiYiXu/Wan2.1-FLF2V-14B-720P-Diffusers"

image_encoder = CLIPVisionModel.from_pretrained(model_id, subfolder="image_encoder", torch_dtype=torch.float32)
vae = AutoencoderKLWan.from_pretrained(model_id, subfolder="vae", torch_dtype=torch.float32)
pipe = WanImageToVideoPipeline.from_pretrained(
    model_id, vae=vae, image_encoder=image_encoder, torch_dtype=torch.bfloat16
)
pipe.to("cuda")

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")

def aspect_ratio_resize(image, pipe, max_area=720 * 1280):
    aspect_ratio = image.height / image.width
    mod_value = pipe.vae_scale_factor_spatial * pipe.transformer.config.patch_size[1]
    height = round(np.sqrt(max_area * aspect_ratio)) // mod_value * mod_value
    width = round(np.sqrt(max_area / aspect_ratio)) // mod_value * mod_value
    image = image.resize((width, height))
    return image, height, width

def center_crop_resize(image, height, width):
    # Calculate resize ratio to match first frame dimensions
    resize_ratio = max(width / image.width, height / image.height)
    
    # Resize the image
    width = round(image.width * resize_ratio)
    height = round(image.height * resize_ratio)
    size = [width, height]
    image = TF.center_crop(image, size)
    
    return image, height, width

first_frame, height, width = aspect_ratio_resize(first_frame, pipe)
if last_frame.size != first_frame.size:
    last_frame, _, _ = center_crop_resize(last_frame, height, width)

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."

output = pipe(
    image=first_frame, last_image=last_frame, prompt=prompt, height=height, width=width, guidance_scale=5.5
).frames[0]
export_to_video(output, f"yiyi_test_7_wan-ff2v.mp4", fps=16)

yiyi_test_5_out.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.

[a-r-r-o-w]

Thanks!

[a-r-r-o-w]

Is this not backwards breaking? 👀

[yiyixuxu]

i will test it out :)

[a-r-r-o-w]

LMK if you'd like me to help add the tests and docs!

[yiyixuxu]

@a-r-r-o-w sounds good!