The invoke-ai team is excited to be able to share the release of InvokeAI 2.0 - A Stable Diffusion Toolkit, a project that aims to provide enthusiasts and professionals both a suite of robust image creation tools. Optimized for efficiency, InvokeAI needs only ~3.5GB of VRAM to generate a 512x768 image (and less for smaller images), and is compatible with Windows/Linux/Mac (M1 & M2).
InvokeAI was one of the earliest forks of the core CompVis repo (formerly lstein/stable-diffusion), and recently evolved into a full-fledged community driven and open source stable diffusion toolkit named InvokeAI. Version 2.0.0 of the tool introduces an entirely new WebUI Front-end with a Desktop mode, and an optimized back-end server that can be interacted with via CLI or extended with your own fork.
This version of the app improves in-app workflows leveraging GFPGAN and Codeformer for face restoration, and RealESRGAN upscaling - Additionally, the CLI also supports a large variety of features:
- Inpainting
- Outpainting
- Negative Prompts (prompt unconditioning)
- Textual Inversion
- Improved Quality for Hi-Resolution Images (Embiggen, Hi-res Fixes, etc.)
- And more...
Release 2.0.1 corrects a bug in image generation when using the k_samplers at high step counts. It also makes the legacy dream.py script work more reliably.
Future updates planned included UI driven outpainting/inpainting, robust Cross Attention support, and an advanced node workflow for automating and sharing your workflows with the community.