LTX 2.3 Image to Video
Anchor the first frame with an image, then animate it with stronger fidelity and steadier motion.
This path is for cases where the opening frame already matters. You keep more control over subject, styling, and identity while letting the model build motion from the source image.
Input
Workflow setup
Upload start image
Anchor the first frame.
Optional end image
Add an end frame for a transition shot.
Motion prompt
Describe how the image should move.
Without an image, the prompt defines the scene and visual direction.
Generation settings
Tune duration, resolution, aspect, FPS, and audio.
Run
Open this workflow
Result
Preview
Why This Path
Pick the right LTX workflow faster
Each mode exists for a different starting point: speech, prompt, still frame, continuation, or a local retake.
Best when a first frame or reference look must stay recognizable.
Pro mode is stronger for cleaner detail and steadier visual continuity.
Useful for character tests, posters, stills, and design frames.
Prompt guidance helps define motion instead of inventing the subject.
Production Fit
Use Cases
Where this workflow is most useful inside a real content pipeline.
Poster to motion
Turn a designed frame into a moving hero visual.
Character motion tests
Animate a locked look without changing identity too much.
Mood loops
Use one still to generate a premium motion vignette.
FAQ
Frequently Asked Questions
Short answers for the practical questions people usually ask when choosing a workflow.
Why choose image-to-video?
It gives you stronger control over subject appearance and the initial composition.
What should the prompt describe?
Prompt the motion, atmosphere, and camera behavior rather than re-describing the whole subject.
Why use Pro here?
It is the better fit when detail retention and continuity matter more than raw iteration speed.