This is a Unreal Engine 5 implementation of Stable Diffusion. It provides a streamlined GUI inside Unreal Engine to easily generate game-ready textures among other features. You can run Automatic1111 or InvokeAI as the backend server.
Quick links: [Discord Server]
This plugin supports several SD backends. You can find individual installation instructions below. Install Automatic1111 Stable Diffusion and/or InvokeAI
-
[1a] Follow the install instructions at AUTOMATIC1111/stable-diffusion-webui and get that running normally
-
[1b] Follow the install instructions at invoke-ai/InvokeAI and get that running normally (WIP, use the legacy_InvokeAI in the meantime before I add support for their new API)
Launch the main UI from the playbar here: Main ui:
Choose backend server and automatically launch it from the "Start Server" button. Make sure the plugin settings have the correct path
- Realtime - toggle that will generate the images without freezing unreal, but may generate slower. Off by default
- Seamless - Forces SD to generate seamless images. Sometimes you could try to have this off and instead type seamless in the prompt
- If DeepBump is installed (optional), you will get extra options. This allows right-click action on any texture in the content browser for Normal/Height/Curvature map generation. This will generate those textures based on the diffuse map and import them to the project.
Most docs here link to InvokeAI's as they are very detailed and show usecases and syntax
- v0.8.0 (03 April 2023)
- Major rework
- Added support for Automatic1111 backend server
- Converted from content to C++ plugin
- Moved config settings to plugin settings
- Adding WIP ChatGPT prompting support
- v0.6.0 (30 October 2022)
- Added Img2Img support
- Cleaned up UI.
- Fixed reset button bugs.
- Added export of texture if source file not found.
- Added more sliders to UI
- v0.5.0 (23 October 2022)
- initial version with prompt/negative prompts, cfg, steps features
If the images won't generate due to VRAM, try lowering the resolution or temporarily load an empty level in unreal to generate images.
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. If you are unfamiliar with how to contribute to GitHub projects, here is a Getting Started Guide.
A full set of contribution guidelines, along with templates, are in progress, but for now the most important thing is to make your pull request against the "development" branch, and not against "main". This will help keep public breakage to a minimum and will allow you to propose more radical changes.
This fork is at the moment handled by me, with the main features/backend API coming from InvokeAI.
For support, please use this repository's GitHub Issues tracking service. Feel free to send me an email if you use and like the plugin.
Original portions of the software are Copyright (c) 2023 Emil Eldstål