-
Notifications
You must be signed in to change notification settings - Fork 29k
How to make your own Inpainting model
w-e-w edited this page May 23, 2023
·
4 revisions
Making your own inpainting model is very simple:
- Go to Checkpoint Merger
- Select "Add Difference"
- Set "Multiplier" to 1.0
- Set "A" to the official inpaint model (SD-v1.5-Inpainting)
- Set "B" to your model
- Set "C" to the standard base model (SD-v1.5)
- Set name as whatever you want, probably (your model)_inpainting
- Set other values as preferred, ie probably select "Safetensors" and "Save as float16"
- Hit merge
- Use your new model in img2img inpainting tab
The way this works is it literally just takes the inpainting model, and copies over your model's unique data to it. Notice that the formula is A + (B - C), which you can interpret as equivalent to (A - C) + B. Because 'A' is 1.5-inpaint and 'C' is 1.5, A - C is inpainting logic and nothing more. so the formula is (Inpainting logic) + (Your Model).
This is the Stable Diffusion web UI wiki. Wiki Home
Setup
- Install and run on NVidia GPUs
- Install and run on AMD GPUs
- Install and run on Apple Silicon
- Install and run on Intel Silicon (external wiki page)
- Install and run via container (i.e. Docker)
- Run via online services
Reproducing images / troubleshooting
Usage
- Features
- Command Line Arguments and Settings
- Optimizations
- Custom Filename Name and Subdirectory
- Change model folder location e.g. external disk
- User Interface Customizations
- Guides and Tutorials
Developers