discussion

Show HN: InvokeAI, an open source Stable Diffusion toolkit and WebUI

Name: Show HN: InvokeAI, an open source Stable Diffusion toolkit and WebUI
Author: sophrocyne

sophrocyne October 10, 2022

414 copies 414 likes

Hey everyone!<p>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).<p>InvokeAI was one of the earliest forks off of the core CompVis repo (formerly lstein&#x2F

Prompt

Hey everyone!<p>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&#x2F;Linux&#x2F;Mac (M1 &amp; M2).<p>InvokeAI was one of the earliest forks off of the core CompVis repo (formerly lstein&#x2F;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.<p>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...<p>Future updates planned included UI driven outpainting&#x2F;inpainting, robust Cross Attention support, and an advanced node workflow for automating and sharing your workflows with the community.<p>We&#x27;re excited by the release, and about the future of democratizing the ability to create. Check out the repo (<a href="https:&#x2F;&#x2F;github.com&#x2F;invoke-ai&#x2F;InvokeAI" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;invoke-ai&#x2F;InvokeAI</a>) to get started, and join us on Discord (<a href="https:&#x2F;&#x2F;discord.gg&#x2F;ZmtBAhwWhy" rel="nofollow">https:&#x2F;&#x2F;discord.gg&#x2F;ZmtBAhwWhy</a>)!

Comments

More Prompts

View all

Development

ComfyUI Advanced Workflow Designer

Design and optimize ComfyUI node workflows for Stable Diffusion. Covers ControlNet, IP-Adapter, inpainting, upscaling, and multi-pass generation pipelines.

Community

Creative

SDXL Photorealistic Portrait Master

Generate stunning photorealistic portraits with SDXL. Covers lighting setups, camera simulation, skin texture, and professional photography techniques.

Community

Technical

A Guide to Prompt Engineering for Stable Diffusion

Technical deep-dive into prompt engineering covering token limits, attention mechanisms, prompt weighting with parentheses and numerical values, embedding manipulation, and A/B testing different prompt structures with reproducible experiments.

Weights & Biases (geekyrakshit)

Best Practices

Prompt Engineering for Stable Diffusion

Covers the full prompt engineering workflow including subject specification, style references, quality boosters, camera and lighting terminology, negative prompt strategies, and CFG scale tuning for different prompt styles.

Portkey.ai

Negative Prompts

Negative Prompts for Stable Diffusion: The Complete Guide (2026)

Exhaustive guide to negative prompts covering common negative terms, negative embeddings (EasyNegative, bad_prompt), weighting strategies, model-specific negative prompts, and common mistakes like over-weighting.

ImageToPrompt.dev

Technical

Prompting & Prompt Weighting in Diffusers

Official Hugging Face documentation on prompt weighting techniques in the Diffusers library, covering Compel syntax, numerical weights, blend operations, and conjunction prompts for advanced control over generation.

Hugging Face