LTX-2 19B image-to-video animates your photo into a 5 to 20 second clip with a stereo soundtrack, at 480p, 720p or 1080p in the photo's own shape. Describe the motion and the sound; billing is per second and there is no content filter.
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
riad-lanterns-saffron-silk A 16:9 still in, a 16:9 clip out with sound from the same pass. The rooftop, the lanterns and the saffron silk come from the image; the prompt adds the lean back, the fingertip tracing her cheek and neck, the turn to the lens and the push-in, and names three sound sources so the oud, the city and the lantern chains are generated with the picture.
- 612031
- 720p
- 5s
- Output6s
prop-plane-night-start The track is close to silent for the first seconds and the engine comes in as the propeller turns over, so the sound follows the action in the picture.
- 510515
- 720p
- 6s
- Output6s
paddle-steamer-two Two people and one small action: a word in the ear and a shared laugh. The paddle wheel and the crowd behind the glass carry over from the still.
- 510516
- 720p
- 6s
This example starts at $0.014 per output second. The Playground updates the estimate when you change the settings.