Check it out here: https://iterate.world

We’ve become obsessed with generative AI. In the last year it feels like “AI” went from highly specialized, domain specific rankers and classifiers to intelligent feeling creative tools that we can build more general apps around.

While the models are incredible, it still feels like day 0 for applications and interface. Our vision is to build an accessible progressive disclosure interface that lets beginners make great images then learn from experts making masterpieces. We hope playing with the image generator feels a bit like tinkering with a synth… you’ll discover a phrase that gives your images a special tone, riff on it, then file it away in a preset for later.

FEATURES

- Streams: Streams are workspaces where you can iterate on an image or theme. Streams have presets.

- Presets: presets like —trip, —photog, —graphite are like stylistic configurations for the image generator (like a preset on a synthesizer). You can make your own for the community to use. This gives iterate prompts a shared command language that users can change.

- GPT-powered prompt completion: type a few words and see what GPT thinks could make it a good prompt. As your stream progresses, it will make suggestions based on the most liked images in the stream. This was a fun feature to build. More on that in this tweet: https://twitter.com/_0_/status/1641854387759743001

TECH

Under the hood we use DALL-E 2, Stable Diffusion (1.5 and 2.1), Openjourney V2, and Material Stable Diffusion for image generation. We use ChatGPT for pre-processing prompts and surfacing completions in the UI. You can configure the model per prompt or per stream with --commands. Before you ask, the Midjourney image generator is incredible and if they release an API, we’ll integrate immediately. If there are other engines you want to play with, let us know.

OPEN

Prompts are always displayed below images and presets always show the configuration so you can copy and improve them. We’re also strong advocates of open source and our last project was an open source devtool. At some point we’d like to open source Iterate.World but as maintainers we know that having an open codebase and fielding community questions incurs a big time cost that we’re not ready to take on yet.

WHAT NEXT

Broadly: better tools to make better images and tools for better making together. I love audio samplers (e.g. MPC, digitakt, sp404, ableton) and I think of the AI image generators a lot like samplers. They provide an interface where you can take a lot of existing work and mash it together in interesting ways. In that regard, I think a lot about how we can make Iterate.World feel more “musical”, how we can improve the workflow for live collaboration and let you go further with your creations.

Thanks for taking a look, excited to see what ya’ll make! LMK if you have questions or suggestions.