WaveSpeed AI
700+ AI models (Google, OpenAI, ByteDance, Kling, Luma) via one API. Images in <2s, videos in <2min.
Setup
bash1export WAVESPEED_API_KEY="your_key_here"
Key is stored in TOOLS.md or .env file. The skill script is at skills/wavespeed/scripts/wavespeed.js.
Usage
bash1# Image generation 2node wavespeed.js generate --model flux --prompt "sunset over mountains" --output out.png 3node wavespeed.js generate --model seedream --prompt "..." --size 1024x1024 4 5# Image editing (face/portrait-safe — preserves identity) 6node wavespeed.js edit --model nbp --prompt "change bathrobe to black hoodie, dark background" \ 7 --image https://example.com/photo.jpg --output result.png 8 9# Video from image 10node wavespeed.js video --model wan-i2v --prompt "slow cinematic zoom" \ 11 --image https://example.com/frame.jpg --output clip.mp4 12 13# List all aliases 14node wavespeed.js models 15 16# Check task status 17node wavespeed.js status --id task_abc123
Key Models (Quick Reference)
| Task | Alias | Best for |
|---|---|---|
| Edit photo keeping face | nbp | Portrait retouching, outfit/bg change |
| Fast image gen | flux-schnell | Drafts, quick tests |
| Best image quality | flux-pro / seedream | Final outputs |
| Image → Video | wan-i2v | Fast, affordable |
| Premium video | kling / veo | Cinematic quality |
| Text → Video | sora / veo | Story videos |
See references/models.md for full model list with IDs, params, and pricing.
Important Notes
- Image editing (
nbp,nb-edit): always pass images asimages: [url]array — this is required - Face preservation:
google/nano-banana-pro/editis the best model for editing photos while keeping the person's face identical - Output files are saved to current directory by default; use
--outputto specify path - Videos can take 2-5 minutes; script auto-polls with progress indicator
- For multiple input images (multi-reference editing), use
--images url1,url2
