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
25.76k stars 5.32k forks source link

SDXL model config error for inpainting #4148

Closed junhyoung-ew closed 1 year ago

junhyoung-ew commented 1 year ago

https://github.com/huggingface/diffusers/blob/ed2a3584ab2ee59676eb95c884ba2d7bb831f41d/src/diffusers/pipelines/stable_diffusion_xl/pipeline_stable_diffusion_xl_inpaint.py#L643

hi, thank you for inpainting task. I got error that "AttributeError: 'FrozenDict' object has no attribute 'force_upcast'". I check sdxl model, but i didn't found vae.config.force_upcast Can you guide me correctly?

patrickvonplaten commented 1 year ago

Hey @junhyoung-ew,

Can you add a reproducible code snippet please?

junhyoung-ew commented 1 year ago

@patrickvonplaten

I don't know vae.config.force_upcast that what is meaning.

so, i can't fix code.. :(

github-actions[bot] commented 1 year 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.