InvokeAI
by invoke-aiProfessional creative tooling for Stable Diffusion. Unified canvas, layers, workflow tabs — designed for actual production use.
About InvokeAI
InvokeAI is a Python open-source image & vision ai project by invoke-ai. Professional creative tooling for Stable Diffusion. Unified canvas, layers, workflow tabs — designed for actual production use. With 24,000 GitHub stars and 0forks, it's one of the Image & Vision AI tools worth knowing. You can download the source, browse it on GitHub, or read the full setup guide in the README below.
InvokeAI — guide
A canvas, not a prompt box
Most Stable Diffusion front-ends are built around a prompt field and a gallery of results. InvokeAI is built around a canvas you paint on. You generate a base image, then keep working it — mask a region, regenerate just that part, extend past the original frame, stack layers. That difference matters more than any feature list: it is the gap between rolling the dice until something works and steering an image toward what you already have in mind.
Who it fits
People producing images that have to satisfy someone else — a brief, a client, a house style. The inpainting and outpainting tools are the reason to choose it: fixing a hand, replacing a background, or widening a composition are ordinary operations here rather than workarounds.
What it costs to run
It is a Python application you install and run yourself, not a website you sign into. Realistically you want a discrete GPU with 8GB of VRAM or more; less will run, slowly, with smaller models. Checkpoints are multi-gigabyte downloads, so budget disk space as well. Nothing is sent anywhere — the model runs on your hardware, which is the whole point for anyone working on unreleased material.
When to pick something else
If you want to see and rewire every step of the pipeline, ComfyUI exposes the node graph InvokeAI deliberately hides. Choose Invoke when the image is the object of attention; choose Comfy when the pipeline is.
From the project README
<div align="center">
[image: project hero]
Invoke - Professional Creative AI Tools for Visual Media
[![discord badge]][discord link] [![latest release badge]][latest release link] [![github stars badge]][github stars link] [![github forks badge]][github forks link] [![CI checks on main badge]][CI checks on main link] [![latest commit to main badge]][latest commit to main link] [![github open issues badge]][github open issues link] [![github open prs badge]][github open prs link] [![translation status badge]][translation status link]
[[image: Sponsor Invoke]][sponsor link]
</div>
Invoke is a leading creative engine built to empower professionals and enthusiasts alike. Generate and create stunning visual media using the latest AI-driven technologies. Invoke offers an industry leading web-based UI, and serves as the foundation for multiple commercial products.
- Free to use under a commercially-friendly license
- Download and install on compatible hardware
- Generate, refine, iterate on images, and build workflows
[image: Highlighted Features - Canvas and Workflows]
Documentation
| Quick Links |
This is an excerpt from the project's own README, quoted here for reference. Read the full README on GitHub →
InvokeAI — FAQ
Is InvokeAI free?
Yes. It is open-source under the Apache 2.0 licence and runs on your own machine at no cost. The company behind it sells a hosted commercial product, but the self-hosted application is free and complete.
What hardware do I need to run InvokeAI?
A GPU with at least 8GB of VRAM is the practical floor for comfortable use. It will run on less, and on Apple Silicon, but generation gets slow and larger models may not fit. You also need several gigabytes of disk per checkpoint.
How is InvokeAI different from ComfyUI?
InvokeAI puts a paintable canvas first and keeps the pipeline out of your way; ComfyUI puts a node graph first and gives you every step to wire yourself. Invoke suits image-making, Comfy suits pipeline-building.
Does InvokeAI send my images anywhere?
No. Generation happens locally on your own GPU, so prompts and images never leave your machine. That is the main reason people choose a self-hosted tool over a web service for unreleased work.
More Image & Vision AI skills
See all Image & Vision AI →The de-facto web UI for running Stable Diffusion locally. Plugins, LoRAs, ControlNets, img2img, in-painting — it all started here.
Node-based UI for Stable Diffusion. Wire up complex pipelines with full control — the power-user choice.
Meta's foundation model for image segmentation. Click any pixel, get a perfect mask of the object it belongs to.