znxlwm/UGATIT-pytorch

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

2536 stars · 461 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

Official PyTorch implementation of U-GAT-IT, an unsupervised image-to-image translation model using attention modules and adaptive layer-instance normalization (AdaLIN). It trains GAN-based models to translate images between domains, such as selfies to anime portraits.

Use cases

• convert selfie photos to anime style
• train an unsupervised image-to-image translation model
• reproduce U-GAT-IT paper results in PyTorch
• translate images between two unpaired image domains
• experiment with attention-based GAN architectures

When to choose

• you need unsupervised domain-to-domain image translation without paired data
• you want the official reference implementation of the U-GAT-IT paper
• your translation task involves large shape and texture changes, like selfie-to-anime

When to avoid

• you need a maintained production-ready image translation pipeline
• you want paired pix2pix-style translation with aligned training data
• you lack a GPU, since training is memory-intensive

Facets

library · maturity maintenance

image-processing machine-learning deep-learning deep-learning computer-vision image-processing artificial-intelligence python gan image-to-image-translation pytorch attention selfie2anime research-code gpu linux

Member repositories

For agents

markdown · JSON · MCP: product_card(name="znxlwm/UGATIT-pytorch")