Back to Gap Map Model components / Image, video, 3D & music generation

InvokeAI

open source / Overall score: 2.0

InvokeAI is a locally run image-generation application with a unified canvas, a gallery and a node-based workflow editor. It runs the Stable Diffusion, FLUX, Qwen-Image, Z-Image and other image families on the user's own hardware and can call a few hosted models through their APIs. The project is now maintained by its community after the company behind it closed its hosted service.

Openness

5 high confidence

5.0

license: Apache-2.0(OSI)
source: public(invoke-ai/InvokeAI)
core features withheld: no — no ee, enterprise, commercial or proprietary directory

InvokeAI is released under Apache 2.0 with its full source public. Its official hosted platform has closed, and no paid edition of the software exists beside the open one.

https://invoke.ai/ recorded 2026-09-26
"The Invoke.ai hosted platform has been shut down as the founding team joined Adobe. However, Invoke lives on as a thriving open-source project maintained by the community."
https://raw.githubusercontent.com/invoke-ai/InvokeAI/main/LICENSE recorded 2026-09-26
LICENSE body: "Apache License / Version 2.0, January 2004".
https://ungh.cc/repos/invoke-ai/InvokeAI/files/main recorded 2026-09-26
Full file list: no ee/, enterprise/, commercial/ or proprietary/ directory; license files cover bundled model and third-party code.

Adoption

2 high confidence

2.0

Adoption is measured as PyPI downloads of the invokeai package, which is the application itself and links back to the repository.

https://pypi.org/pypi/invokeai/json recorded 2026-09-26
PyPI invokeai: project_urls Source = https://github.com/invoke-ai/InvokeAI/, summary "A full-featured AI-assisted image generation environment designed for creatives and enthusiasts."
https://pypistats.org/api/packages/invokeai/recent recorded 2026-09-26
pypistats for invokeai: last_month 23263.

Capability

2 high confidence

2.0

InvokeAI runs a wide range of image model families locally, with a canvas and a node workflow editor. It is a step below stable-diffusion.cpp because everything it runs on local hardware is an image model; its Wan support is a call to a hosted API.

https://raw.githubusercontent.com/invoke-ai/InvokeAI/main/README.md recorded 2026-09-26
README Model Support: "SD 1.5, SD 2.0, SDXL, SD 3.5 Medium, SD 3.5 Large, CogView 4, Flux.1 Dev ... Qwen Image, Qwen Image Edit, Ideogram 4, ERNIE-Image, ERNIE-Image-Turbo, Nano Banana (API Only), GPT Image (API Only), Wan (API Only)".

Verified 2026-09-26