when use fa3 backend, diffuser will raise error.
import torch
import numpy as np
from diffusers import WanPipeline, AutoencoderKLWan, WanTransformer3DModel, UniPCMultistepScheduler
from diffusers.utils import export_to_video, load_image
dtype = torch.bfloat16
device = "cuda"
model_id = "Wan-AI/Wan2.2-TI2V-5B-Diffusers"
vae = AutoencoderKLWan.from_pretrained(model_id, subfolder="vae", torch_dtype=torch.float32)
pipe = WanPipeline.from_pretrained(model_id, vae=vae, torch_dtype=dtype)
pipe.to(device)
height = 704
width = 1280
num_frames = 121
num_inference_steps = 50
guidance_scale = 5.0
prompt = "Two anthropomorphic cats in comfy boxing gear and bright gloves fight intensely on a spotlighted stage."
negative_prompt = "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"
with attention_backend("_flash_3"):
output = pipe(
prompt=prompt,
negative_prompt=negative_prompt,
height=height,
width=width,
num_frames=num_frames,
guidance_scale=guidance_scale,
num_inference_steps=num_inference_steps,
).frames[0]
export_to_video(output, "5bit2v_output.mp4", fps=24)
Describe the bug
[FA3] Don't return lse:
Dao-AILab/flash-attention@ed20940
but in the current diffuser version, it is not updated.
https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/attention_dispatch.py#L608
when use fa3 backend, diffuser will raise error.
Reproduction
Logs
System Info
Who can help?
No response