One other task

[leoShen917]

Congrats on your great work and thank you for releasing the code. I would like to ask if it is possible to use this network to repair broken images, such as those with missing parts or unclear, and I wonder if it is possible to provide such precise control. Thanks in advance and really looking forward to your reply!

[MC-E]

I think it is feasible. For instance, Stable Diffusion can be trained to complete the task of image inpainting (https://github.com/CompVis/stable-diffusion/blob/main/scripts/inpaint.py).