# stepfun-ai/Step1X-Edit

A SOTA open-source image editing model, which aims to provide comparable performance against the closed-source models like GPT-4o and Gemini 2 Flash.

Repository: https://github.com/stepfun-ai/Step1X-Edit
Canonical: https://ross.abutalabs.com/products/step1x-edit
Homepage: https://step1x-edit.github.io
Language: Python
License: Apache-2.0
License Family: permissive
Topics: image-editing, reasoning, visual-reasoning
Last push: 2026-04-29T14:31:44+00:00

## Health v2 (maintenance only)
Score: 55/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 79, release rhythm 35, longevity 35
- inputs: {"age_days": 497, "days_push": 126, "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 2256, forks 102 (observed 2026-08-28T04:06:31.396743+00:00)

## What it is
Step1X-Edit is an open-source state-of-the-art instruction-based image editing model from StepFun, designed to rival closed-source editors like GPT-4o and Gemini 2 Flash. It includes model weights, inference code, and the GEdit-Bench evaluation benchmark, with a reasoning-enhanced variant (ReasonEdit).

## Use cases
- edit images with natural language instructions
- open-source alternative to GPT-4o image editing
- remove or replace objects in photos
- change image style via text prompts
- benchmark image editing models with GEdit-Bench
- run reasoning-based image edits locally

## When to choose
- you need high-quality instruction-following image editing without closed-source APIs
- you want a self-hosted editing model with published benchmark results
- you need reasoning-heavy edits like text replacement or multi-step changes

## When to avoid
- you lack a GPU or cannot run large diffusion models locally
- you only need simple programmatic image transforms like cropping or resizing
- you need real-time editing on constrained hardware

## Facets
- artifact type: library
- maturity: active
- function: image-processing, machine-learning, deep-learning
- domain: image-processing, artificial-intelligence, computer-vision
- platform: python
- tags: image-editing, diffusion-model, instruction-following, text-to-image, reasoning-edit, gedit-bench, gpu, linux

## Member repositories
- stepfun-ai/Step1X-Edit (main) score 55

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:31.396743+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 2026-08-30T02:43:43.471951+00:00, confidence not recorded.
  - readme: https://github.com/stepfun-ai/Step1X-Edit (fetched 2026-08-28T04:06:31.396743+00:00, sha 2ede41870cde)
  - homepage: https://step1x-edit.github.io (fetched 2026-08-29T10:23:39.622170+00:00, sha a0f8be051b4c)
- Data as of 2026-08-30T08:39:29.467469+00:00.