Export
The link always opens the latest version of this page.
Ask an AI about it
Open in ChatGPTA new chat that reads this entry from the site Open in ClaudeThe same, in ClaudeShare the link instead of a file, and they will always see the latest version.
Files are a snapshot of today. The live page has anything newer.
MiniMax H3
Open-weights video generation model supporting text, image, audio, and video inputs with native stereo audio output up to 2K resolution and 15 seconds duration
- Category
- multimodal model with audio and image branches 1 source
MiniMax H3 is an open-weights video generation model that accepts text, image, audio, and video inputs and produces video output with native stereo audio support up to 2K resolution and 15 seconds duration.
The model is available on hugging-face1 (confidence: medium). It can be deployed on comfyui2 (confidence: high) and runs on apple-silicon1 (confidence: high).
Facts 2
| Attribute | Value | Confidence | Sources | Cited |
|---|---|---|---|---|
| Vendor | MiniMax | low | 1 | 5 |
| Category | multimodal model with audio and image branches | low | 1 | 4 |
Platform 2
Neighbourhood
Parts 3
Official links
Frequently mentioned together 4
Sources 6
- H3-metal – Native MiniMax-H3 inference for Apple Silicon · Hacker News (YC)
- MiniMax H3 Day-0 Support in ComfyUI: Open Weights, Native Audio, and 2K Video · Hacker News (YC)
- Comparing Six AI Video APIs by Cost, Concurrency, and Reliability · HackerNoon
- How MiniMax-H3-Image Handles High-Resolution AI Image Generation · HackerNoon
- Inside Viggle Remake: LoRA-Based Video Editing With MiniMax-H3 · HackerNoon
5 of 6 sources shown · Pro unlocks the full list