# invoke-ai/InvokeAI

Invoke is a leading creative engine for Stable Diffusion models, empowering professionals, artists, and enthusiasts to generate and create visual media using the latest AI-driven technologies. The solution offers an industry leading WebUI, and serves as the foundation for multiple commercial products.

Repository: https://github.com/invoke-ai/InvokeAI
Canonical: https://ross.abutalabs.com/products/invokeai
Homepage: https://invoke-ai.github.io/InvokeAI/
Language: Python
License: Apache-2.0
License Family: permissive
Topics: ai-art, artificial-intelligence, generative-art, image-generation, img2img, inpainting, latent-diffusion, linux, macos, outpainting, txt2img, windows, stable-diffusion
Last push: 2026-08-25T23:56:19+00:00

## Health v2 (maintenance only)
Score: 99/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 99, longevity 100
- inputs: {"age_days": 1478, "days_push": 8, "days_rel": 8, "gap_med": 9, "n_releases_24m": 54}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 28015, forks 2947 (observed 2026-08-28T04:11:48.056446+00:00)

## What it is
Invoke is a self-hosted, open-source creative engine for AI image generation with Stable Diffusion models (SD 1.5, SDXL, Flux), featuring a professional web UI with a layer-based Unified Canvas and node-based workflow editor. It runs locally on your own GPU hardware and is Apache 2.0 licensed, serving as the foundation for several commercial products.

## Use cases
- generate images from text prompts with stable diffusion locally
- inpaint and outpaint images with an AI canvas editor
- build reproducible node-based image generation workflows
- manage stable diffusion checkpoints, LoRAs, and ControlNet models
- run AI image generation privately on my own GPU
- refine sketches and photos with img2img
- self-host an alternative to cloud AI art services

## When to choose
- you want a polished, production-grade local UI for Stable Diffusion/Flux image generation
- you need layer-based canvas editing with inpainting/outpainting for professional art workflows
- you want to build and share complex node-based generation pipelines
- privacy matters and you need everything running locally on your hardware
- you need a commercially-friendly (Apache 2.0) license

## When to avoid
- you only need a lightweight CLI or scripting interface for batch generation
- you have no compatible GPU hardware
- you want video, audio, or text generation rather than images
- you prefer a fully managed cloud service with no local setup

## Facets
- artifact type: application
- maturity: active
- function: image-processing, stable-diffusion, gpu-computing, web-framework, ui-components, workflow-automation
- domain: artificial-intelligence, image-processing, graphics, self-hosted, web-development
- platform: windows, python, self-hosted
- tags: stable-diffusion, ai-art, txt2img, img2img, inpainting, outpainting, node-based-workflows, unified-canvas, model-manager, local-generation, linux, macos, web-server, gpu

## Member repositories
- invoke-ai/InvokeAI (main) score 99

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:48.056446+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 2026-08-29T16:54:28.468032+00:00, confidence not recorded.
  - readme: https://github.com/invoke-ai/InvokeAI (fetched 2026-08-28T04:11:48.056446+00:00, sha 3e2385c85ae5)
  - homepage: https://invoke-ai.github.io/InvokeAI/ (fetched 2026-08-29T07:51:18.251917+00:00, sha 04e0ad12be42)
  - site_page: http://invoke.ai/start-here/installation (fetched 2026-08-29T07:51:18.261478+00:00, sha c8f26a08c74e)
  - registry_pypi: https://pypi.org/pypi/invokeai/json (fetched 2026-08-29T07:51:18.271202+00:00, sha 5e8464312426)
  - site_page: http://invoke.ai/start-here/manual (fetched 2026-08-29T07:51:18.263892+00:00, sha fdd67aff4411)
  - site_page: http://invoke.ai/troubleshooting/faq (fetched 2026-08-29T07:51:18.266537+00:00, sha ab18f18fad42)
- Data as of 2026-08-30T08:39:29.467469+00:00.