search

huggingface / diffusers

🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch and FLAX.
https://huggingface.co/docs/diffusers
Apache License 2.0
25.92k stars 5.34k forks source link

diffusers0.19.3 #7872

Closed YuzhiChen001 closed 1 week ago

YuzhiChen001 commented 5 months ago

Describe the bug

diffusers0.19.3，in pipeline_controlnet.py， in __call__(),cross_attention_kwargs: Optional[Dict[str, Any]] = None,, but pipe(cross_attention_kwargs={"scale": 0.8}) has problem: File "/lib/python3.8/site-packages/diffusers/models/attention_processor.py", line 322, in forward return self.processor( TypeError: call() got an unexpected keyword argument 'scale'

Reproduction

I don't want to update my diffusers version, is there any other solution? Any help would be greatly appreciated.

Logs

No response

System Info

torch==2.0.1 torchvision diffusers==0.19.3 transformers==4.36.0 xformers==0.0.20 xatlas accelerate cupy-cuda11x==12.2.0 configargparse ipython

Who can help?

@DN6 @yiyixuxu @sayakpaul @DN6

asomoza commented 5 months ago

can you share a fully reproducible code please, we can't help you with what you're sharing (just enough to produce the error).

github-actions[bot] commented 1 month ago

This issue has been automatically marked as stale because it has not had recent activity. If you think this still needs to be addressed please comment on this thread.

Please note that issues that do not follow the contributing guidelines are likely to be ignored.

a-r-r-o-w commented 1 week ago

Closing this issue since 0.19 is a very old version, and due to inactivity. This should be fixed in the past few newer releases. Feel free to open a new issue if any problems still persist