affinelayer/pix2pix-tensorflow

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

5081 stars · 1285 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

A TensorFlow implementation of pix2pix, a conditional GAN that learns a mapping from input images to output images. It is a faithful port of the original Torch implementation, supporting training, testing, and pre-trained models for tasks like facades, edges-to-photos, and day-to-night translation.

Use cases

• translate images from one domain to another with a GAN
• train a pix2pix model on my own paired image dataset
• convert building facades labels into realistic facade photos
• turn sketches or edges into photorealistic images
• run day-to-night or satellite-to-map image translation
• experiment with conditional adversarial networks in TensorFlow

When to choose

• you need a faithful TensorFlow port of the original pix2pix paper
• you have paired input/output image datasets for image-to-image translation
• you want pre-trained models for common pix2pix tasks like facades or edges2cats
• you prefer TensorFlow 1.x and GPU/cuDNN training

When to avoid

• you need PyTorch or modern TensorFlow 2.x support
• you want the latest GAN research features beyond the original pix2pix
• you need an actively maintained project with recent updates
• you lack a GPU and cannot tolerate very slow CPU training

Facets

library · maturity maintenance

machine-learning deep-learning image-processing machine-learning deep-learning image-processing computer-vision python pix2pix gan image-to-image-translation tensorflow generative-models cyclegan linux gpu docker

Member repositories

For agents

markdown · JSON · MCP: product_card(name="affinelayer/pix2pix-tensorflow")