ai-video-generatorlisted
Install: claude install-skill popnow-ai/popnow-skills
# AI video generation with any PopNow model
PopNow serves the leading video models behind a single API key. This skill helps the agent choose a model for the request, quote the exact USD cost and render after the user agrees.
## 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 |
|---|---|
| `bytedance/seedance-2.5/text-to-video` | Cinematic, native audio, 30 s |
| `minimax/h3/text-to-video` | Best value, expressive |
| find with `models --search "kling 4"` | Realistic human motion, edits |
| find with `models --search "wan 3"` | Open-weight family, many tiers |
| find with `models --search "vidu"` | Image-to-video specialist |
## Prompt tips
- Pick by need: lowest cost → MiniMax H3 Lite or Seedance 2.0 Mini; best cinematic look → Seedance 2.5; human motion and edits → Kling 4.0; animate an illustration → Vidu or PixVerse.
- Video is priced per second and by resolution; always quote the exact duration and default to 720p.
- Run `models --modality video` for the full list, including lip-sync, talking avatars and dubbing.
- Vertical 9:16 for Reels, TikTok and Shorts; 16:9 for YouTube and landing pages.
## 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 fo