Fix hunyuan video attention mask dim

[a-r-r-o-w]

Fixes #10453

Reproducer:

import torch
from diffusers import HunyuanVideoPipeline, HunyuanVideoTransformer3DModel
from diffusers.utils import export_to_video

model_id = "hunyuanvideo-community/HunyuanVideo"
transformer = HunyuanVideoTransformer3DModel.from_pretrained(
    model_id, subfolder="transformer", torch_dtype=torch.bfloat16
)
pipe = HunyuanVideoPipeline.from_pretrained(model_id, transformer=transformer, torch_dtype=torch.float16)

# Enable memory savings
pipe.vae.enable_tiling()
pipe.enable_model_cpu_offload()

output = pipe(
    prompt="A cat walks on the grass, realistic",
    height=320,
    width=512,
    num_frames=61,
    num_inference_steps=30,
    num_videos_per_prompt=2,
).frames[0]
export_to_video(output, "output.mp4", fps=15)

hunyuan-2.mp4

hunyuan-1.mp4

cc @Nerogar

[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.

[yiyixuxu]

thanks!