Jun-Yan Zhu

Image-to-Image Translation in PyTorch

Software that can generate photos from paintings, turn horses into zebras, perform style transfer, and more.

Image-to-image translation with conditional adversarial nets

Pytorch implementation of our method for high-resolution (e.g. 2048x1024) photorealistic video-to-video translation.

Synthesizing and manipulating 2048x1024 images with conditional GANs

Interactive Image Generation via Generative Adversarial Networks

Deep learning software for colorizing black and white images with a few clicks.

Contrastive unpaired image-to-image translation, faster and lighter training than cyclegan (ECCV 2020, in PyTorch)

One-step image-to-image with Stable Diffusion turbo: sketch2image, day2night, and more

Custom Diffusion: Multi-Concept Customization of Text-to-Image Diffusion (CVPR 2023)

Pytorch-based tools for visualizing and understanding the neurons of a GAN. https://gandissect.csail.mit.edu/

[ICCV 2025 Best Paper] Official repository for BrickGPT, the first approach for generating physically stable toy brick models from text prompts.