InvokeAI: A Stable Diffusion Toolkit

Formerly known as lstein/stable-diffusion

This is a fork of CompVis/stable-diffusion, the open source text-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, with GPU cards with as little as 4 GB of RAM. It provides both a polished Web interface (see below), and an easy-to-use command-line interface.

Quick links: [Discord Server] [Documentation and Tutorials] [Code and Downloads] [Bug Reports] [Discussion, Ideas & Q&A]

Note: This fork is rapidly evolving. Please use the Issues tab to report bugs and make feature requests. Be sure to use the provided templates. They will help aid diagnose issues faster.

Table of Contents

1. Installation
2. Hardware Requirements
3. Features
4. Latest Changes
5. Troubleshooting
6. Contributing
7. Contributors
8. Support
9. Further Reading

Installation

This fork is supported across multiple platforms. You can find individual installation instructions below.

• Linux

• Windows

• Macintosh

Hardware Requirements

System

You wil need one of the following:

• An NVIDIA-based graphics card with 4 GB or more VRAM memory.
• An Apple computer with an M1 chip.

Memory

• At least 12 GB Main Memory RAM.

Disk

• At least 12 GB of free disk space for the machine learning model, Python, and all its dependencies.

Note

If you have a Nvidia 10xx series card (e.g. the 1080ti), please run the dream script in full-precision mode as shown below.

Similarly, specify full-precision mode on Apple M1 hardware.

Precision is auto configured based on the device. If however you encounter errors like 'expected type Float but found Half' or 'not implemented for Half' you can try starting invoke.py with the --precision=float32 flag:

(invokeai) ~/InvokeAI$ python scripts/invoke.py --precision=float32

Features

Major Features

• Web Server
• Interactive Command Line Interface
• Image To Image
• Inpainting Support
• Outpainting Support
• Upscaling, face-restoration and outpainting
• Reading Prompts From File
• Prompt Blending
• Thresholding and Perlin Noise Initialization Options
• Negative/Unconditioned Prompts
• Variations
• Personalizing Text-to-Image Generation
• Simplified API for text to image generation

Other Features

• Google Colab
• Seamless Tiling
• Shortcut: Reusing Seeds
• Preload Models

Latest Changes

v2.1.0 major changes (2 November 2022)

- [Inpainting](https://invoke-ai.github.io/InvokeAI/features/INPAINTING/) support in the WebGUI
- Greatly improved navigation and user experience in the [WebGUI](https://invoke-ai.github.io/InvokeAI/features/WEB/)
- The prompt syntax has been enhanced with [prompt weighting, cross-attention and prompt merging](https://invoke-ai.github.io/InvokeAI/features/PROMPTS/).
- You can now load [multiple models and switch among them quickly](https://docs.google.com/presentation/d/1WywGA1rny7bpFh7CLSdTr4nNpVKdlUeT0Bj0jCsILyU/edit?usp=sharing) without leaving the CLI.
- The installation process (via `scripts/preload_models.py`) now lets you select among several popular [Stable Diffusion models](https://invoke-ai.github.io/InvokeAI/installation/INSTALLING_MODELS/) and downloads and installs them on your behalf. Among other models, this script will install the current Stable Diffusion 1.5 model as well as a StabilityAI variable autoencoder (VAE) which improves face generation.
-  Tired of struggling with photoeditors to get the masked region of for inpainting just right? Let the AI make the mask for you using [text masking](https://docs.google.com/presentation/d/1pWoY510hCVjz0M6X9CBbTznZgW2W5BYNKrmZm7B45q8/edit#slide=id.p). This feature allows you to specify the part of the image to paint over using just English-language phrases.
-  Tired of seeing the head of your subjects cropped off? Uncrop them in the CLI with the [outcrop feature](https://invoke-ai.github.io/InvokeAI/features/OUTPAINTING/#outcrop).
- Tired of seeing your subject's bodies duplicated or mangled when generating larger-dimension images? Check out the `--hires` option in the CLI, or select the corresponding toggle in the WebGUI.
- We now support textual inversion and fine-tune .bin styles and subjects from the Hugging Face archive of [SD Concepts](https://huggingface.co/sd-concepts-library). Load the .bin file using the `--embedding_path` option. (The next version will support merging and loading of multiple simultaneous models).
<a href="https://invoke-ai.github.io/InvokeAI/CHANGELOG/>Complete Changelog</a>

• v2.0.1 (13 October 2022)

  • fix noisy images at high step count when using k* samplers
  • dream.py script now calls invoke.py module directly rather than via a new python process (which could break the environment)

• v2.0.0 (9 October 2022)

  • dream.py script renamed invoke.py. A dream.py script wrapper remains for backward compatibility.
  • Completely new WebGUI - launch with python3 scripts/invoke.py --web
  • Support for inpainting and outpainting
  • img2img runs on all k* samplers
  • Support for negative prompts
  • Support for CodeFormer face reconstruction
  • Support for Textual Inversion on Macintoshes
  • Support in both WebGUI and CLI for post-processing of previously-generated images using facial reconstruction, ESRGAN upscaling, outcropping (similar to DALL-E infinite canvas), and "embiggen" upscaling. See the !fix command.
  • New --hires option on invoke> line allows larger images to be created without duplicating elements, at the cost of some performance.
  • New --perlin and --threshold options allow you to add and control variation during image generation (see Thresholding and Perlin Noise Initialization
  • Extensive metadata now written into PNG files, allowing reliable regeneration of images and tweaking of previous settings.
  • Command-line completion in invoke.py now works on Windows, Linux and Mac platforms.
  • Improved command-line completion behavior. New commands added:
    • List command-line history with !history
    • Search command-line history with !search
    • Clear history with !clear
  • Deprecated --full_precision / -F. Simply omit it and invoke.py will auto configure. To switch away from auto use the new flag like --precision=float32.

For older changelogs, please visit the CHANGELOG.

Troubleshooting

Please check out our Q&A to get solutions for common installation problems and other issues.

Contributing

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.

Contributors

This fork 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.

Support

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 (c) 2020 Lincoln D. Stein

Further Reading

Please see the original README for more information on this software and underlying algorithm, located in the file README-CompViz.md.