Extension for Automatic1111 and ComfyUI to automatically create masks for Background/Hair/Body/Face/Clothes in Img2Img
Uses the Multi-class selfie segmentation model model by Google.
- 2024-05-26 - Adding facial landmark mask outputs for ComfyUI
- 2024-05-25 - Fixed ComfyUI requirements and install
- 2024-01-01 - Added ComfyUI support
- 2023-11-16 - Initial release
(from Mikubill/sd-webui-controlnet)
- Open "Extensions" tab.
- Open "Install from URL" tab in the tab.
- Enter
https://github.com/djbielejeski/a-person-mask-generator.git
to "URL for extension's git repository". - Press "Install" button.
- Wait 5 seconds, and you will see the message "Installed into stable-diffusion-webui\extensions\a-person-mask-generator. Use Installed tab to restart".
- Go to "Installed" tab, click "Check for updates", and then click "Apply and restart UI". (The next time you can also use this method to update extensions.)
- Completely restart A1111 webui including your terminal. (If you do not know what is a "terminal", you can reboot your computer: turn your computer off and turn it on again.)
- Navigate to your ComfyUI folder, then into the
custom_nodes
folder in aCMD
window and run the following command
git clone https://github.com/djbielejeski/a-person-mask-generator
D:\ComfyUI\custom_nodes>git clone https://github.com/djbielejeski/a-person-mask-generator
- Restart ComfyUI.
Workflow embedded in image, drag into ComfyUI to use.
Masks in this order
- Face
- Background
- Body + Clothes
- Hair