seedancelisted
Install: claude install-skill popnow-ai/popnow-skills
# Seedance video generation
Seedance 2.5 is ByteDance's newest video model: clips up to 30 seconds with native sound, strong camera language and multi-shot storytelling. It animates still images, follows reference images for characters and products, and can extend an existing clip. Seedance 2.0, Fast and Mini are cheaper options.
## 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` | Video from a prompt |
| `bytedance/seedance-2.5/image-to-video` | Animate a still image |
| `bytedance/seedance-2.5/reference-to-video` | Keep characters or products consistent |
| `bytedance/seedance-2.5/video-extend` | Continue an existing clip |
| `bytedance/seedance-2.0-fast/text-to-video` | Cheaper, faster drafts |
## Prompt tips
- Video is billed per second: quote the exact duration and resolution, and default to 720p unless the user asks for more.
- Direct it like a shot list: shot 1 wide establishing, shot 2 close-up, camera dolly in, sound of rain.
- For image-to-video, describe only the motion; the image already defines the look.
- Rendering takes minutes; poll status with pauses rather than resubmitting.
## 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