| name | fal-ai-media |
| description | Generate and edit images and videos via the fal.ai API using models including nano-banana-2, gpt-image-2, kling-v3-std, and veo3.1-fast, routing through the user's FAL_KEY to minimize Zo credit usage. |
| compatibility | Created for Zo Computer |
| metadata | {"author":"marlandoj.zo.computer"} |
fal-ai-media
Image and video generation skill using the fal.ai API with the user's own FAL_KEY.
Usage
bun /home/workspace/Skills/fal-ai-media/scripts/fal-media.ts <command> [options]
Commands
| Command | Description |
|---|
generate | Text-to-image generation |
edit | Image editing / transformation |
video | Image-to-video generation |
t2v | Text-to-video generation |
models | List available models |
Model Selection
- Text in image (titles, thumbnails, labels):
--model gpt-image-2
- Standard generation:
--model nano-banana-2 (default)
- High-quality/campaign:
--model nano-banana-pro
- Video from image:
--model kling-v3-std (default)
- Text-to-video:
--model veo3.1-fast (default)
Examples
bun scripts/fal-media.ts generate --prompt "A serene mountain landscape" --output /home/workspace/Images/mountain.png
bun scripts/fal-media.ts edit --prompt "Change background to sunset" --image /home/workspace/Images/photo.png --output /home/workspace/Images/edited.png
bun scripts/fal-media.ts video --prompt "Camera slowly pans right" --image /home/workspace/Images/scene.png --output /home/workspace/Images/scene.mp4
Notes
- Requires
FAL_KEY in Zo Secrets (Settings > Advanced)
- GPT Image 2 caveats: no PNG transparency, max aspect 3:1, endpoint is
fal-ai/gpt-image-2
- Always save outputs to
/home/workspace/Images/ with descriptive filenames
