mirror of
https://github.com/AUTOMATIC1111/stable-diffusion-webui.git
synced 2025-04-06 12:49:02 +08:00
Updated Features (markdown)
parent
2a2bca6d87
commit
1dba74dd17
@ -34,6 +34,15 @@ Options for inpainting:
|
||||
- erase a part of the picture in an external editor and upload a transparent picture. Any even slightly transparent areas will become part of the mask. Be aware that [some editors](https://docs.krita.org/en/reference_manual/layers_and_masks/split_alpha.html#how-to-save-a-png-texture-and-keep-color-values-in-fully-transparent-areas) save completely transparent areas as black by default.
|
||||
- change mode (to the bottom right of the picture) to "Upload mask" and choose a separate black and white image for the mask (white=inpaint).
|
||||
|
||||
## Inpainting model
|
||||
RunwayML has trained an additional model specifically designed for inpainting. This model accepts additional inputs - the initial image without noise plus the mask - and seems to be much better at the job.
|
||||
|
||||
Download and extra info for the model is here: https://github.com/runwayml/stable-diffusion#inpainting-with-stable-diffusion
|
||||
|
||||
To use the model, you must rename the checkpoint so that its filename ends in `inpainting.ckpt`, for example, `1.5-inpainting.ckpt`.
|
||||
|
||||
After that just select the checkpoint as you'd usually select any checkpoint and you're good to go.
|
||||
|
||||
## Masked content
|
||||
The masked content field determines content is placed to put into the masked regions before they are inpainted.
|
||||
|
||||
|
Loading…
x
Reference in New Issue
Block a user