DFloat11/Wan2.2-I2V-A14B-2-DF11

    pip install -U dfloat11[cuda12]

    pip install git+https://github.com/huggingface/diffusers

    import time
    import torch
    import numpy as np
    import argparse
    from diffusers import WanImageToVideoPipeline
    from diffusers.utils import export_to_video, load_image
    from dfloat11 import DFloat11Model

    parser = argparse.ArgumentParser(description='Image to Video generation using Wan2.2-I2V model')
    parser.add_argument('--cpu_offload', action='store_true', help='Enable CPU offloading')
    parser.add_argument('--image_path', type=str, default="https://huggingface.co/datasets/YiYiXu/testing-images/resolve/main/wan_i2v_input.JPG", help='Path or URL to the input image')
    parser.add_argument('--width', type=int, default=1280, help='Output video width')
    parser.add_argument('--height', type=int, default=720, help='Output video height')
    parser.add_argument('--prompt', type=str, default="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.", help='Prompt for video generation')
    parser.add_argument('--negative_prompt', type=str, default="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", help='Negative prompt for video generation')
    parser.add_argument('--num_frames', type=int, default=81, help='Number of frames to generate')
    parser.add_argument('--guidance_scale', type=float, default=3.5, help='Guidance scale for generation')
    parser.add_argument('--num_inference_steps', type=int, default=40, help='Number of inference steps')
    parser.add_argument('--seed', type=int, default=42, help='Random seed for generation')
    parser.add_argument('--output', type=str, default='i2v_output.mp4', help='Output video path')
    parser.add_argument('--fps', type=int, default=16, help='FPS of output video')

    args = parser.parse_args()

    image = load_image(args.image_path)

    pipe = WanImageToVideoPipeline.from_pretrained("Wan-AI/Wan2.2-I2V-A14B-Diffusers", torch_dtype=torch.bfloat16)

    DFloat11Model.from_pretrained(
        "DFloat11/Wan2.2-I2V-A14B-DF11",
        device="cpu",
        cpu_offload=args.cpu_offload,
        bfloat16_model=pipe.transformer,
    )
    DFloat11Model.from_pretrained(
        "DFloat11/Wan2.2-I2V-A14B-2-DF11",
        device="cpu",
        cpu_offload=args.cpu_offload,
        bfloat16_model=pipe.transformer_2,
    )

    pipe.enable_model_cpu_offload()

    max_area = args.width * args.height
    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))

    generator = torch.Generator(device="cuda").manual_seed(args.seed)

    start_time = time.time()
    output = pipe(
        image=image,
        prompt=args.prompt,
        negative_prompt=args.negative_prompt,
        height=height,
        width=width,
        num_frames=args.num_frames,
        guidance_scale=args.guidance_scale,
        num_inference_steps=args.num_inference_steps,
        generator=generator,
    ).frames[0]
    print(f"Time taken: {time.time() - start_time:.2f} seconds")

    export_to_video(output, args.output, fps=args.fps)

    max_memory = torch.cuda.max_memory_allocated()
    print(f"Max memory: {max_memory / (1000 ** 3):.2f} GB")

    PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True python i2v.py

    PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True python i2v.py --cpu_offload