InvokeAI
App : A product you use directly
Local generation studio with a retouching canvas, more accessible than ComfyUI.
The best power-to-ergonomics compromise in local tools for creatives.
Security reflects where data goes, requested permissions and incidents on record at the verification date. It is not a guarantee of zero risk: check the deployment mode and the connections you enable.
What it does, concretely
Generating images with AI locally often raises an accessibility problem: the most powerful tools require advanced technical knowledge, while online solutions raise privacy and cost concerns. InvokeAI addresses this by offering a complete visual creation studio installed on your own machine, without sending your data to a remote server.
The tool runs via a locally hosted web server, accessible from your browser. It includes a unified canvas for generating, editing, and painting images, a node-based workflow system for automating creative pipelines, and a gallery for organizing and reusing your work. Installation is handled through a dedicated launcher available on GitHub.
InvokeAI is aimed at creatives, illustrators, photographers, and visual media professionals who want to integrate AI into their workflow without relying on a cloud subscription. It supports a wide range of models, including Stable Diffusion 1.5, SDXL, Flux.1 Dev, Flux.1 Kontext, and several API-only models such as GPT Image and Wan.
However, it is not suited for users who do not want to manage a software installation on their computer, or whose hardware lacks a compatible graphics card. Users looking for a fully configuration-free solution will find online alternatives more immediately accessible.
What it offers
- ·Unified canvas for generating, painting, inpainting, and outpainting images within an integrated workspace.
- ·Node-based workflow system for building and sharing custom generation pipelines.
- ·Gallery with board management to store, retrieve, and remix produced images, with full metadata support.
- ·Integrated model manager supporting SD 1.5, SD 2.0, SDXL, SD 3.5, Flux.1 Dev, Flux.1 Kontext, Krea 2, Ideogram 4, GPT Image, and many more.
- ·Object segmentation and selection tools using SAM and SAM2 models.
- ·Upscaling tools to improve the resolution of generated images.
- ·Embedding manager with support for ckpt, diffusers, and some gguf model formats.
- ·Local React-based web UI accessible from any browser without additional installation.
In practice
- Price
- Freemium
- Commercial use
- Commercial use: yes
- Available on
- windows, macos, linux
- Licence
- Apache-2.0
- FR interface
- No
Security and data
- Rating
- Security: nothing to flag
- Your data
- Data stays local
- Maintenance
- Active
- Last release
- 27 September 2026
Links and repository checked on 25 October 2026 · added on 1 September 2022