How to load a custom fine-tuned embeds into the inpainting pipeline？

[anonymoussss]

Hi, thanks for the great work.

I want to know if there is any way to load the new concept obtained by fine-tuned (whether it is textual inversion, dreambooth or others) into the inpainting model? As shown in the textual inversion paper: replace the iphone in the hands of Steve Jobs with .

I only saw examples of the finetune methods (TI, dreambooth) and the inference example of inpainting in this repo , but don't know how the inpainting pipeline loads the embedding obtained from textual inversion finetune. Please help me

[patrickvonplaten]

LoRA should work since: #1884 . For textual inversion there is an open PR: #2009

[github-actions]

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.