InvokeAI
Free, Apache-2.0 image generation you run on your own hardware, built around a layered canvas.
- Starting price
- Free
- Free trial
- Free and open source, no subscription
- Commercial use
- The application is Apache-2.0; the licence of each model you load applies to its output
Overview
InvokeAI is a free and open-source creative engine for AI image generation that runs on your own machine. Its centre is the Unified Canvas, a layer-based surface where generation sits alongside drawing, painting and inpainting, so an image is developed in place rather than re-rolled from a prompt each time. Behind the canvas is a node-based workflow system. It is licensed under Apache-2.0, supports more than twenty-five model architectures, and installs on Windows, macOS on Apple Silicon and Linux, all of which require a suitable GPU.
Our take
This is the option for people whose objection to hosted generators is the hosting rather than the output: local models keep prompts and images on your own hardware, there is no per-image meter, and the permissive licence means the engine can sit inside commercial work without a subscription conversation. What you take on in exchange is the hardware and the setup, and the Apple Silicon restriction rules out Intel Macs outright. The canvas is the reason to pick it over a bare node graph, because retouching a region with brushes and layers is closer to how an illustrator already works than rewriting a prompt is. Support comes from the project community rather than a vendor desk, which is worth weighing if a deadline depends on it.
Key Facts
| Category | |
|---|---|
| Starting price | Free Open source under Apache-2.0. You supply the hardware. |
| Free trial | Free and open source, no subscription |
| Commercial use | The application is Apache-2.0; the licence of each model you load applies to its output |
| Output | Images |
| Hosting | Self-hosted on Windows 10+, macOS on Apple Silicon or Linux, with a GPU |
Screenshots
Placeholders. They are replaced as soon as the vendor sends material, and both open the same short form.
Features
- Where you use it
- Self-hosted application on Windows 10+, macOS (Apple Silicon) and Linux, installed via installer, Docker or manual Python setup
- Text in images
- Depends on the model loaded; the application renders nothing itself
- Customization and control
- Unified Canvas with layers, brush tools and in- and outpainting, node-based workflows, ControlNet, LoRAs, textual inversions, batch generation and upscaling
- Open weights
- Yes, Apache-2.0 application running open-weight models including Stable Diffusion 1.5 and 2.0, SDXL, Flux and CogView 4
- API
- Yes, the self-hosted server exposes an HTTP API built with FastAPI and Socket.IO, with an annotated OpenAPI spec; it is the same interface the web UI runs on
Integrations
Integrations coming soon.
Deployment and Support
- Deployment
-
- On-premise
- Support
-
- Community forum
- Onboarding
-
- Documentation and knowledge base
- Company size
-
- Freelancers
- Small and mid-sized
Suitability
| Industry | Freelancers | Small and mid-sized | Enterprise |
|---|---|---|---|
| Agencies | Not stated | Not stated | Not stated |
| Architecture & Engineering | Not stated | Not stated | Not stated |
| Consulting | Not stated | Not stated | Not stated |
| Media & Creative | Stated as a fit | Stated as a fit | Not stated |
| Technology | Not stated | Not stated | Not stated |
The table combines the industries the vendor addresses with the company sizes the tool is aimed at. An empty cell means the combination is not stated, not that it is ruled out.
Pros and Cons
Strengths
- Free and Apache-2.0, a permissive licence for commercial work
- Layer-based Unified Canvas with brushes, inpainting and outpainting
- Local models run on your own hardware, so their prompts and output stay there; a few models in the list are marked API only
- Supports 25+ model architectures with LoRA, textual inversion and ControlNet management
Limitations
- You supply and maintain a suitable GPU
- macOS support is Apple Silicon only
- Community support rather than a vendor helpdesk
Pricing
-
Open source
$0
Apache-2.0 licence, self-hosted on your own hardware.
Best For
Alternatives and Comparisons
What users say
Reviews
-
0 reviews
- Ease of use
- Not rated yet
- User interface
- Not rated yet
- Onboarding
- Not rated yet
- Support and service
- Not rated yet
- Value for money
- Not rated yet
- Features
- Not rated yet
No reviews yet. Nothing has been published here yet, and no score is shown. How a review is checked before it appears is described below.
How we check reviews
Reviews are not published yet. The form on a tool's page works and reaches us, but nothing from it appears on this site, so no score here is based on a review. The rules below are the ones that will apply once reviews go live.
Every review is read by a person before it appears. We require a working email address and use it to come back to the author, so a review has a reachable sender rather than being anonymous. We publish positive and negative reviews alike, we pay nothing and offer nothing for a review, and we accept none that was bought or incentivised.
What we cannot do is verify a purchase. There is no shop here and no account, so whether the author really used the tool rests on what they tell us, plus the plausibility of what they write. We say so rather than implying a check that does not exist.
A vendor cannot have a review removed, cannot buy one, and cannot have one changed. Paid placement and a paid listing have no effect on which reviews appear or on any score.
Share your experience
Write a Review
Last verified:
Ready to take a closer look at InvokeAI
The link goes straight to the vendor. Some links on this site are affiliate links.
Visit InvokeAI