Add a "Inpaint upload" function for inpainting model #1312
OedoSoldier
started this conversation in
Ideas
Replies: 3 comments 1 reply
|
Yes it could be very useful, i dont know pass my manual masks to controlnet |
0 replies
|
You can actually use "Inpaint upload" in Stable Diffusion img2img, which allows you to upload both an image and its mask. Then you can enable controlnet's inpainting at the bottom and do not upload an image there. Then you can click on generate and it will inpaint only in the masked region in your predefined mask. |
1 reply
|
For anyone who finds this, sd-webui-segment-anything has this feature as of the time of writing. You can install it from the Extensions tab. Best used with img2img. |
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment

Uh oh!
There was an error while loading. Please reload this page.
So we can upload a mask image rather than drawing it in WebUI. Currently, in txt2img mode, we cannot upload a mask image to preciously control the inpainting area.
All reactions