fal-model-selector
Installation
SKILL.md
FAL Model Selector
Quick decision guide for choosing fal.ai models. Read references/ for full parameters.
Key Concepts
Image-to-Video vs Reference-to-Video
| Image-to-Video | Reference-to-Video | |
|---|---|---|
| Input | 1 image (starting frame) | Multiple images (1-5 references) |
| Purpose | Animate that exact image | Maintain subject consistency in new scenes |
| The image becomes... | The first frame of the video | A "template" for what subject looks like |
| Camera/scene | Starts from that exact view | Can be completely different scenes |
Image-to-Video = "animate this exact image"
- Product photo → animate it rotating
- Portrait → make the person smile/blink