# timothybrooks/instruct-pix2pix

Repository: https://github.com/timothybrooks/instruct-pix2pix
Canonical: https://ross.abutalabs.com/products/instruct-pix2pix
Language: Python
License: NOASSERTION
License Family: other
Last push: 2024-03-03T21:54:00+00:00

## Health v2 (maintenance only)
Score: 31/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 95
- inputs: {"age_days": 1332, "days_push": 913, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 6885, forks 579 (observed 2026-08-28T04:09:51.114950+00:00)

## What it is
PyTorch implementation of InstructPix2Pix, a diffusion-based model that edits images according to natural language instructions (e.g., 'turn him into a cyborg'). Built on the CompVis stable-diffusion codebase and includes a CLI editor and a Gradio interactive editing app.

## Use cases
- edit photos with text instructions
- turn a person into a cyborg with ai
- instruction-based image editing
- run instruct-pix2pix on my own images
- launch a gradio app for image editing
- change image style via natural language prompt

## When to choose
- you want to edit images using natural-language instructions rather than masks or manual tools
- you have a GPU with sufficient VRAM and want a local, scriptable editing pipeline
- you want to build on or fine-tune an instruction-based editing model for research

## When to avoid
- you lack a GPU or cannot adjust default configurations for lower VRAM
- you need a polished end-user photo editor rather than a research codebase
- you need a general text-to-image generator instead of instruction-based editing

## Facets
- artifact type: library
- maturity: maintenance
- function: image-processing, machine-learning, deep-learning
- domain: image-processing, artificial-intelligence, computer-vision
- platform: python, cross-platform
- tags: stable-diffusion, image-editing, diffusion-models, pytorch, gradio, research, gpu, linux

## Member repositories
- timothybrooks/instruct-pix2pix (main) score 31

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:51.114950+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 2026-08-29T17:41:39.665379+00:00, confidence not recorded.
  - readme: https://github.com/timothybrooks/instruct-pix2pix (fetched 2026-08-28T04:09:51.114950+00:00, sha 314022ff845b)
- Data as of 2026-08-30T08:39:29.467469+00:00.