# sail-sg/EditAnything

Edit anything in images  powered by segment-anything, ControlNet, StableDiffusion, etc. (ACM MM)

Repository: https://github.com/sail-sg/EditAnything
Canonical: https://ross.abutalabs.com/products/editanything
Language: Python
License: Apache-2.0
License Family: permissive
Last push: 2025-02-23T04:58:34+00:00

## Health v2 (maintenance only)
Score: 33/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 8, release rhythm 35, longevity 88
- inputs: {"age_days": 1242, "days_push": 556, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3422, forks 202 (observed 2026-08-28T04:08:03.854127+00:00)

## What it is
Edit Anything is a Python application for text-guided image editing and generation, combining Segment Anything, ControlNet, BLIP2, and Stable Diffusion. It offers interactive segmentation-based editing via scripts and a Gradio demo on Hugging Face.

## Use cases
- edit objects in a photo with a text prompt
- inpaint part of an image using a segmentation mask
- generate an image conditioned on SAM segmentation masks
- change clothes or hair in a portrait photo
- sketch to image generation with mask alignment
- merge regions from two images into one

## When to choose
- you want segmentation-mask-guided image editing with Stable Diffusion
- you need a research demo combining SAM and ControlNet
- you want to run interactive click-based segmentation editing locally

## When to avoid
- you need a polished consumer photo editor
- you lack a GPU or don't want to download large diffusion models
- you need a maintained library API rather than research scripts

## Facets
- artifact type: application
- maturity: maintenance
- function: image-processing, stable-diffusion, machine-learning
- domain: image-processing, artificial-intelligence, deep-learning
- platform: python
- tags: segment-anything, controlnet, inpainting, image-editing, gradio, diffusion-models, web-server, gpu

## Member repositories
- sail-sg/EditAnything (main) score 33

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:03.854127+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:38:09.277246+00:00, confidence not recorded.
  - readme: https://github.com/sail-sg/EditAnything (fetched 2026-08-28T04:08:03.854127+00:00, sha bf4ff7e1faca)
- Data as of 2026-08-30T08:39:29.467469+00:00.