FlyAIgh
An AI video canvas organised by shot, not by wires
What it does
Most AI canvases hand you a node graph, and the board turns to spaghetti. FlyAIgh organises around the shot instead: every clip carries its own assembly panel where characters, props and reference images are made in place — nothing to wire up first. Drag out of a finished clip and its last two seconds become the continuation, so motion connects. Describe an idea and the AI director writes the shot list. Sora 2, VEO 3.1, Kling V3, Midjourney on one wallet. PH code producthuntFLY: +15 credits.
Multi-model AI video and image generation platform. Access the leading models in one place.
Your AI studio — a workflow canvas built from scratch, and an inspiration director that turns one line into a film. Every idea you have deserves to be made. Sora 2, VEO 3.1, Seedance 2.5, Kling V3, Midjourney, Nano Banana Pro — the flagship video and image models, all on one credit wallet. The exact cost of a generation is shown before you run it, with no separate account to open at any vendor. New models simply appear, no plan upgrade required. One sentence becomes a film with shots, a cast and real continuity. The AI director opens up the concept, fixes a visual style, writes the shot list, and locks characters, props and locations into reusable assets so the same face carries the whole…from flyaigh.com
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 · 16d 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 · 16d ago · simedw.com