The default for text-to-video — cinematic motion with real camera moves.
Kling 2.5 Turbo Pro turns a written prompt into a five or ten second shot, and it is the strongest general text-to-video model on comfyarts. What separates it from earlier video models is that motion is coherent over the whole clip: subjects keep their shape as they move, and camera language in the prompt — a slow push in, an orbit, a crane up — is actually executed rather than approximated by drifting the frame.
Video is billed per second, so a ten second clip costs twice a five second one. Prompt the shot as a director would: name the camera move, the subject action and the light, and keep it to one continuous take. Asking for a cut inside a single generation is the most common way to get an incoherent clip.
Per-second billing makes video the most expensive thing on the site — a ten second clip runs into thousands of credits. Kling 1.6 Standard is materially cheaper for tests.
| Price | 494 credits per second — about 45c per second |
|---|---|
| Type | Video |
| Provider | fal |
| Aspect ratios (3) | 16:9, 9:16, 1:1 |
| Durations | 5s, 10s |
Credit prices are the live studio rates. Cash equivalents are approximate at starter-pack rates and improve on the larger packs — see pricing.
Every AI model on comfyarts — video models, prices and measured capabilities side by side.