LTX 2.5 text-to-video is Lightricks' long-form model, turning a written brief into one continuous clip of 5 to 20 seconds. Choose 16:9 or 9:16 at 720p, 1080p, 2K or 4K; a generated soundtrack comes with every clip.
Workbench
These examples were written for this endpoint. Replace the prompt and sample media URLs with your own accessible inputs, then check the current quote and model availability before submitting.
- Output5s
bedside-pov First person: the camera is the person lying against the headboard, and the brief says so in its opening line before describing anything else. That one sentence is what turns an observed scene into one happening to the viewer, and it ends with a fingertip tapped on the lens.
- 720p
- 16:9
- 5s
- Output20s
arena-gate-to-cages `duration_seconds` is at `20`, the top of the range, and the brief says "no cuts" in as many words: one unbroken move that starts at a gate, crosses a packed terrace and ends somewhere else entirely. A long continuous take is where camera path and scene continuity have to survive together, so the prompt describes the journey rather than listing images. Rendered at `1080p` in `16:9`, the shape a walking shot needs.
- 1080p
- 16:9
- 20s
- Output5s
opera-staircase The full arc - descent, fabric, crane move - written as one paragraph and generated as a single take.
- 720p
- 16:9
- 5s
- Output5s
ramen-stall A cel-shaded brief rather than a photographic one. Style is carried entirely by the wording - there is no style field on this family.
- 720p
- 16:9
- 5s
This example starts at $0.09 per output second. The Playground updates the estimate when you change the settings.