Fantasy-Studio/Paint-by-Example

Health v2 · maintenance only

Flags: no_releases no_license

Adoption not part of the score

1252 stars · 113 forks observed · 2026-08-28

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

Paint by Example is a PyTorch implementation of exemplar-based image editing with diffusion models, letting users fill masked regions of an image using a reference exemplar image instead of text prompts. It accompanies the arXiv paper 2211.13227 and provides pretrained checkpoints, a test benchmark, and a Hugging Face demo.

Use cases

• fill a masked region of a photo using a reference object image
• edit images with exemplar-guided diffusion instead of text prompts
• run the Paint by Example pretrained model on my own images
• reproduce the paper's quantitative benchmark results
• try exemplar-based inpainting in a Hugging Face demo

When to choose

• you need reference-image-guided inpainting rather than text-guided editing
• you want to build on or study the Paint by Example diffusion approach
• you need a single-forward-pass editing model without iterative optimization

When to avoid

• you need text-prompt-based image editing only
• you require a production-ready product with active maintenance and a clear license
• you lack a GPU or cannot run PyTorch diffusion models

Facets

library · maturity maintenance

image-processing machine-learning deep-learning computer-vision image-processing deep-learning python diffusion-models stable-diffusion image-editing exemplar-based inpainting pytorch research-code gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="Fantasy-Studio/Paint-by-Example")