omeregev/click2mask
[AAAI 2025] Official Implementation for "Click2Mask: Local Editing with Dynamic Mask Generation" Paper.
This tool helps graphic designers, marketers, and content creators quickly add new objects to existing images with precise control. You provide an image, click on the exact spot where you want a new object, and type a simple text description of what to add. The system then generates the new object, perfectly integrated into the image at your specified location.
Use this if you need to perform local image edits by adding new elements to an image, guided only by a single click and a short text prompt, without needing to manually define masks.
Not ideal if you require complex, multi-object scene generation from scratch or need to make global style changes to an entire image.
Stars
20
Forks
3
Language
Python
License
—
Category
Last pushed
Jan 22, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/omeregev/click2mask"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
PRIS-CV/DemoFusion
Let us democratise high-resolution generation! (CVPR 2024)
mit-han-lab/distrifuser
[CVPR 2024 Highlight] DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Models
Tencent-Hunyuan/HunyuanPortrait
[CVPR-2025] The official code of HunyuanPortrait: Implicit Condition Control for Enhanced...
giuvecchio/matfuse
MatFuse: Controllable Material Generation with Diffusion Models (CVPR2024)
Shilin-LU/TF-ICON
[ICCV 2023] "TF-ICON: Diffusion-Based Training-Free Cross-Domain Image Composition" (Official...