PaddlePaddle/PaddleGAN
PaddlePaddle GAN library, including lots of interesting applications like First-Order motion transfer, Wav2Lip, picture repair, image editing, photo2cartoon, image style transfer, GPEN, and so on.
Built on the PaddlePaddle framework, it provides unified training and inference pipelines for 20+ classic and state-of-the-art GAN architectures using standardized config-file-based workflows. The library implements domain-specific optimizations including latent space manipulation (StyleGAN2 face editing), multi-scale video processing (PP-MSVSR for super-resolution), and composite restoration pipelines that chain multiple models for tasks like historical video enhancement. Integration with AI Studio enables browser-based experimentation and deployment without local GPU requirements.
8,065 stars. No commits in the last 6 months.
Stars
8,065
Forks
1,248
Language
Python
License
Apache-2.0
Category
Last pushed
Jul 03, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/PaddlePaddle/PaddleGAN"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
yunjey/domain-transfer-network
TensorFlow Implementation of Unsupervised Cross-Domain Image Generation
taesungp/contrastive-unpaired-translation
Contrastive unpaired image-to-image translation, faster and lighter training than cyclegan (ECCV...
tohinz/ConSinGAN
PyTorch implementation of "Improved Techniques for Training Single-Image GANs" (WACV-21)
sagiebenaim/DistanceGAN
Pytorch implementation of "One-Sided Unsupervised Domain Mapping" NIPS 2017
ZPdesu/SEAN
SEAN: Image Synthesis with Semantic Region-Adaptive Normalization (CVPR 2020, Oral)