- This is Extension for AUTOMATIC1111's Stable Diffusion Web UI
- Add feature to change CLIPTextModel and CLIPTokenizer
-
Open
Extensions
on webui -
Install from URL
-
Install
- Open "settings"
- Input CLIP address for your needs
This extension will exchange CLIP at "after model Loaded".
It means,
-
no change applied until model re-loaded if you change setting
-
also no change applied until model re-loaded if you Disable this extension
You should care about which CLIP is now applied.
This function may cause problem with model merge / training.
In "Setting" tab | Sample |
---|---|
Enable CLIP Changer | |
Specify CLIPTextModel to use. | openai/clip-vit-large-patch14 |
Specify CLIPTokenizer to use. | openai/clip-vit-large-patch14 |
Supported CLIPTextModel, CLIPTokenizer is diffusers
from transformers import CLIPTextModel, CLIPTokenizer
-
Run test with,
openai/clip-vit-large-patch14
openai/clip-vit-large-patch14-336
-
sample image