fal-ai/marlin/find

Marlin is a 2B video VLM tuned for the two questions developers actually want to ask of their videos: what is happening, and when?
Inference
Commercial use

Input

Type # to reference inputs.

Additional Settings

Customize your input with more control.

Result

Idle
From 1.0 to 2.0.

What would you like to do next?

Your request will cost $0.015 per 1000 token.

Logs