StarryKit
AI visual design editor for presentations, posters & more
What it does
StarryKit is an AI-powered visual creation platform that helps you create presentations, posters, reports, and marketing materials, with designs you can actually edit. Go from idea to finished design faster. Create with AI, refine your work, and customize every detail without starting from templates or spending hours fixing AI-generated designs.
Create polished slides, posters, social posts, and more from a prompt. Start free, explore ideas quickly, and refine every design in StarryKit.
StarryKit is an AI visual design workspace for creating presentations, posters, and other editable visual documents. Describe what you need, refine the result with AI and direct editing, and start creating for free . See how it works Start with a prompt, explore visual directions, and refine the result without returning to a blank canvas. StarryKit keeps the brief, generated work, and direct edits in one connected flow. StarryKit brings the estimated generation cost of a design page below one cent. Explore more directions, make more revisions, and produce editable work—without letting production costs pile up. One image output or one estimated hour of design work is normalized to one visual…from starrykit.com
Does the same job
all alternatives →More growth this month
the category →
AstraPixels▲267A pixel-art solar system at its real current positions.
Growth · 29d ago · astrapixels.com

Launched alongside, August 2026
the whole month →- TL
Life & fun · 10d ago · louisabraham.github.io


- SA
Hello HN! I found that picking out plausible but diverse skin tones for my digital art and game development projects was kind of difficult, and I got curious about if there was a way to define a color space that made it easy. I've built a color picker and procedural generation algorithm based on the space as well as a bunch of other fun js features and demos throughout the page that use the equations. If you find it interesting, I have lots of explanations of how I built it and what properties the space has. The methodology might be a bit shaky, but hopefully the result is as helpful for…
Life & fun · Aug 2026 · toneyalexander.github.io


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 · 16d ago · simedw.com