minimax-h3listed
Install: claude install-skill popnow-ai/popnow-skills
# MiniMax H3 (Hailuo) video generation
MiniMax H3 powers Hailuo video. It is one of the best-value video models on PopNow: expressive motion and faces, native audio, clips up to 30 seconds or 2K. HighSpeed and Lite are faster and cheaper, Max raises quality, and LoRA variants apply custom styles.
## Models
These are the PopNow model paths at the time of writing. Confirm them with `models` before use; newer versions appear there first.
| Model path | Best for |
|---|---|
| `minimax/h3/text-to-video` | Video from a prompt |
| `minimax/h3/image-to-video` | Animate a still image |
| `minimax/h3/reference-to-video` | Consistent characters from references |
| `minimax/h3/video-extend` | Continue a clip |
| `minimax/h3-max/text-to-video` | Highest quality tier |
## Prompt tips
- A strong default for budget video; start at 720p and short durations, then scale up.
- Describe facial expression and body language; H3 is particularly good at emotion.
- Run `models --search "h3"` to see HighSpeed, Lite, X and LoRA variants and their schemas.
## Setup and cost
Requires Python 3.8+ and a PopNow API key in `POPNOW_API_KEY`. Create a dedicated key at https://popnow.ai/api/console/keys and restrict its models, IPs and spending caps. Keep the key in the agent's secret or environment settings: never ask for it in chat, pass it as a command argument, print it or commit it.
The skill is free. Generation is paid from a **separate prepaid API USD balance** (https://popnow.ai/api/console/bill