InvokeAI
by invoke-ai
Invoke is a web-based tool for generating and editing images with AI models such as Stable Diffusion, SDXL and Flux. It runs on your own computer and includes a canvas for painting and editing, a gallery, and node-based workflows.
- Stars
- 28.9k
- Licence
- Apache-2.0
- Runs on
- A gpu machine, with a GPU
- Setup
- Moderate
- Language
- TypeScript
- Age
- 1532 days
What you can do with it
- Generate images from text prompts or from existing pictures using a range of AI models
- Edit and extend images with inpainting and outpainting on the Unified Canvas
- Build and share repeatable node-based workflows for consistent image production
Make money with it
You could sell AI-generated artwork, product visuals or custom image-editing services to clients, provided the licences of the models you use allow commercial work.
An idea, not financial advice. Check the licence before charging for anything built on it.
Ways a business could use it
- Create product mockups, social media graphics and ad imagery in-house instead of paying for stock images or subscriptions
- Offer image creation or touch-up services to clients, using workflows to keep results consistent
Can you use it commercially?
Free to use, change and sell, including in paid products. Keep the copyright notice.
Not legal advice. Read the project's licence file before building a product on it.
Getting it running
Download the Invoke Launcher from the GitHub releases page, then use it to install and update the app and download models.
Follow the official instructions in the project README.
Things to check
- Needs a reasonably powerful graphics card for good performance with local models
- Model licences vary and some restrict commercial use, so check each one
- API-only models (Nano Banana, GPT Image, Wan) need paid third-party access
Who's talking about it
Checked 27 Oct 2026. Summary drafted by AI from the project's README.
