this post was submitted on 26 Apr 2024
5 points (77.8% liked)
Stable Diffusion
4210 readers
11 users here now
Discuss matters related to our favourite AI Art generation technology
Also see
Other communities
founded 1 year ago
MODERATORS
you are viewing a single comment's thread
view the rest of the comments
view the rest of the comments
I think there's a ControlNet preprocessor that does this.
Some segmentation stuff seems close but they only separate objects, they don't add objects. Best workflow I can think of with minimal editing is doing I2I, creating a mask for the new object, then using the mask on the original image.