The AI Edition

The AI Edition

Share this post

The AI Edition
The AI Edition
Stable Diffusion Extensions and Follow-Ups

Stable Diffusion Extensions and Follow-Ups

Discover the latest and greatest extensions of Stable Diffusion text-to-image AI

Sep 06, 2022
∙ Paid
3

Share this post

The AI Edition
The AI Edition
Stable Diffusion Extensions and Follow-Ups
Share

It has been an exciting few weeks since Stability Diffusion became open-source and accessible to use by everyone for free. Various extensions and applications of Stability Diffusion started appearing very quickly. High-quality open-source software makes it very easy to everyone to start using and building on top of it. Kudos to HuggingFace 🤗 and Stability AI developers for their high-quality implementation and model training.

You can argue that many people got a headstart with their ideas as another text-to-image technology DALLE-2 has been out in public for a few months. But DALLE-2 is proprietary and closed-source, meaning that apart from being creative with our text prompts it was impossible to extend it in other ways.

stable diffusion dalle 2
Interest in Stable Diffusion and DALLE-2 on Google

To my surprise, Stable Diffusion quickly outpaced DALLE-2 in terms of interest. I am very excited to see how this graph will evolve over time, but I have no doubts that Stable Diffusion (or other high-quality and high-fidelity open-source text-to-image technologies) will continue outpacing closed-access software like DALLE-2.

Now to the fun part, let’s go over the exciting and important extensions of stable diffusions that have been released in the last few weeks.

Human Language Technology is a reader-supported publication about AI and Natural Language Processing. To receive new posts and support my work, consider becoming a paid subscriber.

This post is for paid subscribers

Already a paid subscriber? Sign in
© 2025 hal
Privacy ∙ Terms ∙ Collection notice
Start writingGet the app
Substack is the home for great culture

Share