MiniMax H3 (Hailuo 3)
Create AI videos with text, images, and reference clips
What it does
MiniMax H3 (Hailuo 3) turns text, images, and reference clips into AI video up to 2K with synchronized sound. Explore the browser workflow at https://minimax-h3.im/ for fast visual experiments and short-form concepts.
MiniMax H3 (Hailuo 3) turns text, images, and reference clips into AI video up to 2K with synchronized sound. Try the free online generator — no software to install.
Just add the material you need. The generator will use it automatically. Only live routes are selectable. Your prompt stays in place when you switch. The files shown on the left are the exact ordered references used for each example. The playable video on the right is the real generated result. The characters, arena, and soundtrack are separate inputs. MiniMax H3 receives the exact ordered files shown here and uses each @ reference in the production prompt below. Create a six-second 16-bit pixel-art side-scrolling duel. Use @image1 as the exact hero design, @image2 as the exact rival design, and @image3 as the arena. Both characters enter, exchange two readable attacks, a bright impact…from minimax-h3.im
Does the same job
all alternatives →
MiniMax H3 Video20d ago · minimaxh3-video.com · ▲1Directed AI videos from briefs and creative references
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