Bitwright
Draw fifty sprites that look like one artist made them.
What it does
The problem with AI art in a game is never the first image. It is the fiftieth. Every generation is an independent roll, so nothing matches and you cannot build a set. Bitwright never generates an image. The model writes a description and your browser draws it, so a sprite is a named palette plus a stack of parts. Tick "match the open sprite" and the next one inherits that palette, viewpoint and detail. Sprites drawn a week apart belong together. Every part stays editable afterwards.
Describe a sprite and get pixel art back you can take apart. It matches the style your game already uses, and every colour stays yours to change. 5 free.
Pixel art from a sentence, drawn to sit beside what you already have. Not a flat picture either: every colour and every piece of it stays yours to change afterwards. Hand it something you already made and the next one arrives in the same clothes. Same angle, same size, same palette. Within reason: it works inside a style, it will not invent one for you. Change your mind at two in the morning. Repaint it, pull a piece off, make it twice the size. Open any of the things below and you can see straight through to how it was put together. Cut to your tile size, and it knows what should move. A lamp flickers. A crate does not, because a wobbling crate is a bug rather than a feature. A village…from bitwright.app
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, 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 · 17d ago · simedw.com