jolibrain/joliGEN
Generative AI Image and Video Toolset with GANs and Diffusion for Real-World Applications
Implements semantic-preserving image-to-image translation across GANs, diffusion, and consistency models with customizable discriminators (projected, vision-aided, transformer-based) and generators (ResNet, ViT, UNet, HDiT) that maintain bounding boxes, masks, and class labels during transformation. Includes a production-ready REST API server, FID/PSNR quality metrics, and advanced augmentation strategies (APA, discriminator noise injection) for unpaired training on tasks like sim-to-real, object insertion/removal, and style transfer while preserving annotations.
280 stars.
Stars
280
Forks
41
Language
Python
License
—
Category
Last pushed
Mar 17, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/jolibrain/joliGEN"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related models
zhangmozhe/Deep-Exemplar-based-Video-Colorization
The source code of CVPR 2019 paper "Deep Exemplar-based Video Colorization".
naver-ai/StyleKeeper
Official Pytorch implementation of "StyleKeeper: Prevent Content Leakage using Negative Visual...
ali-vilab/AnyDoor
Official implementations for paper: Anydoor: zero-shot object-level image customization
lixiaowen-xw/DiffuEraser
DiffuEraser is a diffusion model for video inpainting, which performs great content completeness...
ironjr/semantic-draw
Official code for the CVPR 2025 paper "SemanticDraw: Towards Real-Time Interactive Content...