Hunyuan1.5 use attention masks with variable-length sequences. For best performance, we recommend using an attention backend that handles padding efficiently.
We recommend installing kernels (pip install kernels) to access prebuilt attention kernels.
You can check our documentation to learn more about all the different attention backends we support.
import torch
dtype = torch.bfloat16
device = "cuda:0"
from diffusers import HunyuanVideo15ImageToVideoPipeline, attention_backend
from diffusers.utils import export_to_video, load_image
pipe = HunyuanVideo15ImageToVideoPipeline.from_pretrained("hunyuanvideo-community/HunyuanVideo-1.5-Diffusers-480p_i2v_step_distilled", torch_dtype=dtype)
pipe.enable_model_cpu_offload()
pipe.vae.enable_tiling()
generator = torch.Generator(device=device).manual_seed(1)
image = load_image("https://huggingface.co/datasets/YiYiXu/testing-images/resolve/main/wan_i2v_input.JPG")
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."
with attention_backend("_flash_3_hub"): # or `"flash_hub"/"flash_varlen_hub"` if you are not on H100/H800
video = pipe(
prompt=prompt,
image=image,
generator=generator,
num_frames=121,
num_inference_steps=12,
).frames[0]
export_to_video(video, "output.mp4", fps=24)
to use default attention backend
import torch
dtype = torch.bfloat16
device = "cuda:0"
from diffusers import HunyuanVideo15ImageToVideoPipeline
from diffusers.utils import export_to_video, load_image
pipe = HunyuanVideo15ImageToVideoPipeline.from_pretrained("hunyuanvideo-community/HunyuanVideo-1.5-Diffusers-480p_i2v_step_distilled", torch_dtype=dtype)
pipe.enable_model_cpu_offload()
pipe.vae.enable_tiling()
generator = torch.Generator(device=device).manual_seed(1)
image = load_image("https://huggingface.co/datasets/YiYiXu/testing-images/resolve/main/wan_i2v_input.JPG")
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."
video = pipe(
prompt=prompt,
image=image,
generator=generator,
num_frames=121,
num_inference_steps=12,
).frames[0]
export_to_video(video, "output.mp4", fps=24)