from diffusers import HunyuanVideoImageToVideoPipeline, HunyuanVideoTransformer3DModel
from diffusers.utils import load_image, export_to_video

# Available checkpoints: "hunyuanvideo-community/HunyuanVideo-I2V" and "hunyuanvideo-community/HunyuanVideo-I2V-33ch"
model_id = "hunyuanvideo-community/HunyuanVideo-I2V"
transformer = HunyuanVideoTransformer3DModel.from_pretrained(
    model_id, subfolder="transformer", torch_dtype=torch.bfloat16
)
pipe = HunyuanVideoImageToVideoPipeline.from_pretrained(
    model_id, transformer=transformer, torch_dtype=torch.float16
)
pipe.vae.enable_tiling()
pipe.to("mps")

prompt = "A man with short gray hair plays a red electric guitar."
image = load_image(
    "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/guitar-man.png"
)

output = pipe(image=image, prompt=prompt).frames[0]
export_to_video(output, "output.mp4", fps=15)