Segment Anything for Stable Diffusion WebUI. Automatically generate high-quality segmentations/masks for images by clicking or text prompting. Aim for connecting WebUI and ControlNet with Segment Anything and GroundingDINO to enhance Stable Diffusion/ControlNet inpainting (both single image and batch process), enhance ControlNet semantic segmentation, automate image matting and create LoRA/LyCORIS training set.
081b81cf87
|
||
|---|---|---|
| .github/ISSUE_TEMPLATE | ||
| javascript | ||
| models/segment-everything | ||
| scripts | ||
| .gitignore | ||
| README.md | ||
README.md
Segment Everything for Stable Diffusion Webui
This extension aim for helping stable diffusion webui users to use segment everything to do stable diffusion inpainting.
How to use
Step 1:
Download this extension to ${sd-webui}/extensions use whatever way you like (git clone or install from UI)
Step 2:
Download segment-everything model from here to ${sd-webui-segment-everything}/models/segment-everything
Step 3:
- Launch webui and switch to img2img mode.
- Upload your image, left click for positive prompt (black dot), right click for negative prompt (red dot), left click any dot again to cancel the prompt.
- Click
Preview Segmentationbutton - Choose your favorite segmentation and check
Copy to Inpaint Upload - Switch to
Inpaint upload. There is no need to upload another image or mask, just leave them blank. Write your prompt, configurate and clickGenerate.
Demo
Future Plan
I plan to support text->object detection->segmentation from Grounded Segment Anything in the near future. Stay tuned!
Contribute
Disclaimer: I have not thoroughly tested this extension, so there might be bugs. Bear with me while I'm fixing them :)
If you encounter a bug, please submit a issue.
I welcome any contribution. Please submit a pull request if you want to contribute