Attach a still and it moves, with your composition preserved.
This is the image-to-video variant of Kling 2.5 Turbo Pro. You supply a starting frame and a description of what should happen, and it animates from that image rather than inventing a scene. The composition, colour and subject of your still are the ones that end up in the clip.
That control is why it is usually the better route to a good video. Generating a still is cheap and repeatable — you can iterate on Flux Schnell until the framing is exactly right — while generating video is expensive and hard to steer. Getting the frame perfect first and animating it costs less than re-rolling text-to-video until the composition lands.
It needs an image — this model cannot run from text alone. Use plain Kling 2.5 for text-to-video.
| 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.