Skip to content


project logo

discord badge

latest release badge github stars badge github forks badge

github open issues badge github open prs badge

InvokeAI is an implementation of Stable Diffusion, the open source text-to-image and image-to-image generator. It provides a streamlined process with various new features and options to aid the image generation process. It runs on Windows, Mac and Linux machines, and runs on GPU cards with as little as 4 GB of RAM.


This project is rapidly evolving. Please use the Issues tab to report bugs and make feature requests. Be sure to use the provided templates as it will help aid response time.

InvokeAI Features#

The InvokeAI Web Interface#

Image Management#

Model Management#

Prompt Engineering#

InvokeAI Configuration#

Important Changes Since Version 2.3#


Behind the scenes, InvokeAI has been completely rewritten to support "nodes," small unitary operations that can be combined into graphs to form arbitrary workflows. For example, there is a prompt node that processes the prompt string and feeds it to a text2latent node that generates a latent image. The latents are then fed to a latent2image node that translates the latent image into a PNG.

The WebGUI has a node editor that allows you to graphically design and execute custom node graphs. The ability to save and load graphs is still a work in progress, but coming soon.

Command-Line Interface Retired#

The original "invokeai" command-line interface has been retired. The invokeai command will now launch a new command-line client that can be used by developers to create and test nodes. It is not intended to be used for routine image generation or manipulation.

To launch the Web GUI from the command-line, use the command invokeai-web rather than the traditional invokeai --web.


This version of InvokeAI features ControlNet, a system that allows you to achieve exact poses for human and animal figures by providing a model to follow. Full details are found in ControlNet

New Schedulers#

The list of schedulers has been completely revamped and brought up to date:

Short Name Scheduler Notes
ddim DDIMScheduler
ddpm DDPMScheduler
deis DEISMultistepScheduler
lms LMSDiscreteScheduler
pndm PNDMScheduler
heun HeunDiscreteScheduler original noise schedule
heun_k HeunDiscreteScheduler using karras noise schedule
euler EulerDiscreteScheduler original noise schedule
euler_k EulerDiscreteScheduler using karras noise schedule
kdpm_2 KDPM2DiscreteScheduler
kdpm_2_a KDPM2AncestralDiscreteScheduler
dpmpp_2s DPMSolverSinglestepScheduler
dpmpp_2m DPMSolverMultistepScheduler original noise scnedule
dpmpp_2m_k DPMSolverMultistepScheduler using karras noise schedule
unipc UniPCMultistepScheduler CPU only

Please see 3.0.0 Release Notes for further details.


Please check out our Troubleshooting Guide to get solutions for common installation problems and other issues.


Anyone who wishes to contribute to this project, whether documentation, features, bug fixes, code cleanup, testing, or code reviews, is very much encouraged to do so.

Please take a look at our Contribution documentation to learn more about contributing to InvokeAI.


This software is a combined effort of various people from across the world. Check out the list of all these amazing people. We thank them for their time, hard work and effort.


For support, please use this repository's GitHub Issues tracking service. Feel free to send me an email if you use and like the script.

Original portions of the software are Copyright © 2022-23 by The InvokeAI Team.

Last update: September 19, 2023
Created: September 15, 2022