[RFC]: FastWan2.2-TI2V-5B-FullAttn-Diffusers output doesn't follow input image

[nanwanj]

Motivation.

I'm testing TI2V mode by using the code https://github.com/hao-ai-lab/FastVideo/blob/main/examples/inference/basic/basic_wan2_2_ti2v.py

The output looks good:

wan.mp4

However, If i just change one line, from "model_name = "Wan-AI/Wan2.2-TI2V-5B-Diffusers"" to "model_name = "FastVideo/FastWan2.2-TI2V-5B-FullAttn-Diffusers"", The output doesn't follow input image:

fastwan.mp4

Here's the code I'm using to run FastWan2.2-TI2V-5B-FullAttn-Diffusers:

from fastvideo import VideoGenerator

OUTPUT_PATH = "video_samples_fastwan_5B_ti2v"
def main():
    model_name = "FastVideo/FastWan2.2-TI2V-5B-FullAttn-Diffusers"
    generator = VideoGenerator.from_pretrained(
        model_name,
        # FastVideo will automatically handle distributed setup
        num_gpus=1,
        use_fsdp_inference=False, # set to True if GPU is out of memory
        dit_cpu_offload=True,
        vae_cpu_offload=False,
        text_encoder_cpu_offload=True,
        pin_cpu_memory=True, # set to false if low CPU RAM or hit obscure "CUDA error: Invalid argument"
        # image_encoder_cpu_offload=False,
    )

    # I2V is triggered just by passing in an image_path argument
    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."
    image_path = "https://huggingface.co/datasets/YiYiXu/testing-images/resolve/main/wan_i2v_input.JPG"
    video = generator.generate_video(prompt, output_path=OUTPUT_PATH, save_video=True, image_path=image_path)

if __name__ == "__main__":
    main()

Can anyone please help and let's know if this is a model issue or we're not running the code correctly?

Thanks

Proposed Change.

No

Feedback Period.

No response

CC List.

No response

Any Other Things.

No response

Before submitting a new issue...

• Make sure you already searched for relevant issues.

[jzhang38]

yes while being a TI2V model, we only distill this with T2V. So this behaviour is expected.