djbielejeski/a-person-mask-generator
Extension for Automatic1111 and ComfyUI to automatically create masks for Background/Hair/Body/Face/Clothes in Img2Img
Leverages Google's MediaPipe Multi-class Selfie Segmentation model to detect and isolate specific anatomical regions with pixel-level precision. Includes iterative mask refinement that crops to detected areas and re-runs segmentation for improved accuracy on high-resolution or distant subjects. Deploys as native custom nodes in ComfyUI or as a Web UI extension for Automatic1111, with additional facial landmark detection outputs available.
394 stars.
Stars
394
Forks
47
Language
Python
License
MIT
Category
Last pushed
Feb 10, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/djbielejeski/a-person-mask-generator"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related models
civitai/civitai
A repository of models, textual inversions, and more
lobehub/sd-webui-lobe-theme
🅰️ Lobe theme - The modern theme for stable diffusion webui, exquisite interface design, highly...
daniandtheweb/sd.cpp-webui
A lightweight Gradio WebUI for stable-diffusion.cpp.
wladradchenko/wunjo.wladradchenko.ru
Wunjo CE: Face Swap, Lip Sync, Control Remove Objects & Text & Background, Restyling, Audio...
v8hid/infinite-zoom-automatic1111-webui
infinite zoom effect extension for AUTOMATIC1111's webui - stable diffusion