The difference between SDXL and SDXL-inpainting is that SDXL-inpainting has an additional 5 channel inputs for the latent feature of masked images and the mask.
I have tried to modify by myself but there seem like some bugs
I modified the config.yaml in repositories/generative-models/configs/inference to support for 9 channel input and modified the repositories/generative-models/sgm/modules/diffusionmodules/wrappers.py to concat with additional 5 channels x = torch.cat([x, c['c_concat'][0]],dim=1) in line29.
It would be helpful if you can support for the current SDXL inpainting models.
Is there an existing issue for this?
What would your feature do ?
Support for SDXL-inpainting models.
Proposed workflow
x = torch.cat([x, c['c_concat'][0]],dim=1)
in line29.Additional information
No response