Iterate.World multiplayer AI image generator
Hi HN, we’re Peter, Monica, Elliot, and Alex from Iterate.World. We’re building a multiplayer AI image generator. 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…
What it does
In the maker’s words, at launch
Hi HN, we’re Peter, Monica, Elliot, and Alex from Iterate.World. We’re building a multiplayer AI image generator. 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.
Does the same job
all alternatives →
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, April 2023
the whole month →
- G4
Hi HN, Today we’re launching GPT-4 answers on Phind.com, a developer-focused search engine that uses generative AI to browse the web and answer technical questions, complete with code examples and detailed explanations. Unlike vanilla GPT-4, Phind feeds in relevant websites and technical documentation, reducing the model’s hallucination and keeping it up-to-date. To use it, simply enable the “Expert” toggle before doing a search. GPT-4 is making a night-and-day difference in terms of answer quality. For a question like “How can I RLHF a LLaMa model”, Phind in Expert mode delivers a…
AI · 2023 · phind.com
