Janspiry/Palette-Image-to-Image-Diffusion-Models

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1833 stars · 238 forks observed · 2026-08-28

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

An unofficial PyTorch implementation of the Palette paper on image-to-image diffusion models, supporting tasks like inpainting, uncropping, and colorization. It includes a distributed training pipeline with DDP, EMA, metrics, and pretrained example models.

Use cases

• implement palette image-to-image diffusion model in pytorch
• inpaint images with a diffusion model
• train a ddpm for image restoration
• colorize grayscale photos with deep learning
• outpaint or uncrop images using diffusion
• distributed multi-gpu training of diffusion models

When to choose

• you want a working PyTorch reference implementation of Palette for research or experimentation
• you need diffusion-based inpainting with pretrained example checkpoints
• you want a distributed training template for DDPM-style models

When to avoid

• you need a production-ready image restoration service with support
• you lack GPU resources, since training diffusion models is computationally heavy
• you need the unfinished tasks like uncropping or colorization fully validated

Facets

library · maturity maintenance

machine-learning deep-learning image-processing deep-learning computer-vision image-processing python diffusion-models ddpm pytorch image-to-image inpainting colorization image-restoration unofficial-implementation gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="Janspiry/Palette-Image-to-Image-Diffusion-Models")