InvokeAI, an open source Stable Diffusion toolkit and WebUI
Hey everyone! Excited to be able to share the release of `InvokeAI 2.0 - A Stable Diffusion Toolkit`, an open source project that aims to provide both enthusiasts and professionals 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 off of the core CompVis repo (formerly lstein/stable-diffusion), and recently evolved into a full-fledged community driven and open source stable…
In plain words
InvokeAI is an open-source Stable Diffusion toolkit with a web interface for generating images. Designed for both enthusiasts and professionals, it runs efficiently on modest hardware, requiring only 3.5GB of VRAM for 512x768 image generation. The software works on Windows, Linux, and Mac (including M1 and M2 chips), offering both a desktop mode and a command-line interface with an extensible backend server for customization.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
Hey everyone! Excited to be able to share the release of `InvokeAI 2.0 - A Stable Diffusion Toolkit`, an open source project that aims to provide both enthusiasts and professionals 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 off of the core CompVis repo (formerly lstein/stable-diffusion), and recently evolved into a full-fledged community driven and open source stable diffusion toolkit titled InvokeAI. The new version 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 - Prompt Unconditioning - Textual Inversion - Improved Quality for Hi-Resolution Images (Embiggen, Hi-res Fixes, etc.) - And more... 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. We're excited by the release, and about the future of democratizing the ability to create. Check out the repo (https://github.com/invoke-ai/InvokeAI) to get started, and join us on Discord (https://discord.gg/ZmtBAhwWhy)!
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 26d ago · cactuscompute.com
Launched alongside, October 2022
the whole month →- I3
Hey HN, I 3d scanned the interior of the Great Pyramid / Khufu's pyramid for the Giza Project this summer and just finished the guided version to share. Would love feedback and/or problems you encounter. I used both a Leica BLK 360 and Matterport Pro 2 to do the scanning and the Matterport SDK for the web viewer. Matterport's web display with Three.js has been the most accessible to a wide audience in the past (previous iterations are in Unity and Unreal, but difficult to download over slower connections). I've been interviewing social studies teachers around the 6th grade level to…
Dev tools · 2022 · giza.mused.org
- RO
Last time I posted this it didn't garner much interest. There have been lots of improvements and fixes since the last release. Quick list of features: - Workspaces - Tabs - Nested Folders - Lots of context menus - Response history - Plugins - Runs fully in the browser and runs offline if necessary - Chrome and Firefox extension to bypass CORS restrictions - Desktop builds for all platforms - GraphQL support - Import collections exported from Postman and Insomnia - Simple user friendly interface I built this because I love Insomnia but wanted a portable version that I could run in the…
Dev tools · 2022 · restfox.dev
Micro SaaS HQ▲672Profitable Micro SaaS ideas, supportive community
Life & fun · 2022 · microsaashq.com
- AR
APIs are a little like the open road—always waiting, full of opportunity, but hardly utilized. So here’s America, composed of several APIs that paint a vivid, real-time picture of a good old-fashioned road trip. Get local classifieds and photos. Tune into local radio stations. Talk wit other drivers. And more. Exploring the country by car was an invaluable experience for me during my time in the states. I’ve since moved to Barcelona, and find myself missing the territory. This is my attempt at recreating the magic.
Life & fun · 2022 · 4m3ric4.com