Janspiry/Palette-Image-to-Image-Diffusion-Models
PyTorch implementation of Palette, a diffusion model for image-to-image tasks including inpainting, uncropping, and colorization.
Not currently ranked — collecting fresh signals.
star history
This repository provides an unofficial PyTorch implementation of the Palette paper, which uses conditional diffusion models for image-to-image translation. The implementation includes U-Net architecture with attention mechanisms adapted from guided diffusion, encodes gamma conditioning, and supports distributed training (DDP) with EMA. The project covers three main tasks: image inpainting on CelebaHQ and Places2 datasets, uncropping, and colorization, with evaluation metrics including FID and IS scores.
Frequently asked
- What is Janspiry/Palette-Image-to-Image-Diffusion-Models?
- PyTorch implementation of Palette, a diffusion model for image-to-image tasks including inpainting, uncropping, and colorization.
- Is Palette-Image-to-Image-Diffusion-Models open source?
- Yes — Janspiry/Palette-Image-to-Image-Diffusion-Models is open source, released under the MIT license.
- What language is Palette-Image-to-Image-Diffusion-Models written in?
- Janspiry/Palette-Image-to-Image-Diffusion-Models is primarily written in Python.
- How popular is Palette-Image-to-Image-Diffusion-Models?
- Janspiry/Palette-Image-to-Image-Diffusion-Models has 1.8k stars on GitHub.
- Where can I find Palette-Image-to-Image-Diffusion-Models?
- Janspiry/Palette-Image-to-Image-Diffusion-Models is on GitHub at https://github.com/Janspiry/Palette-Image-to-Image-Diffusion-Models.