Skip to content

LTX 2.5 / Image to video

LTX 2.5 product ads: build a three-shot sequence

A three-shot product ad can give each generation a clear purpose: establish the item, show one detail and end with a readable offer. This is easier to direct than asking a single clip to rotate a product, demonstrate it and produce perfect advertising text.

Assign one job to each shot

The opening establishes the product's silhouette. The middle shot highlights a verified detail such as texture or a visible compartment. The ending gives the viewer time to read a call to action added in the editor. If the item is real, use approved photographs rather than relying on a text prompt to reproduce it.

Keep lighting and background descriptions consistent. A sudden change from a bright studio to a dramatic night scene can make the sequence feel like unrelated products even when each shot looks attractive.

Build the ad

  1. Prepare one wider product image and one detail image.
  2. Animate each with LTX Image to Video using modest motion.
  3. Select only sections that preserve the product accurately.
  4. Add the final offer, brand mark and audio mix in an editor.

Example detail prompt

PROMPT RECIPE / ADAPT TO YOUR SOURCE

Preserve the fabric bag and close-up composition from the image. A soft light passes slowly over the woven texture while the camera remains almost still. Keep the stitching and pocket outline stable. Clean studio presentation, quiet airy sound.

Review the commercial message

Do not let generated movement imply a feature you have not verified. A bag appearing waterproof in an invented rain scene is not evidence of a waterproof rating. Keep prices and terms as editable factual copy. Review the complete ad silently and with sound, checking that the product is understandable before the offer appears and that the final frame has enough reading time.

REVIEWED JOLLYAI IMPLEMENTATION

The workflow behind the guide

Uploaded source + motion brief → image/text conditioning → configured LTX 2.5 generation graph → decoded video and audio.

Inputs, presets & access
PRO. Prepare the source composition and check the current preset before generation.
Implementation note
JollyAI retains ltx2 workflow identifiers while remapping model components to LTX 2.5. The configured graph contains video and audio generation paths. Access is PRO; available duration and quality presets are shown in the playground. Downloaded-file metadata determines the delivered size and duration.

Configuration reviewed September 20, 2026. Your current playground controls and plans page determine availability. Prompt recipes above are suggestions, not guarantees or claimed test results.

Open Image to video ↗

Sources and useful next steps

The implementation notes describe JollyAI's reviewed local integration. Upstream capabilities and licences may differ from the settings available here.

Found an outdated setting or a reproducible problem? Contact JollyAI with the workflow and job reference. Keep account tokens and private input files out of public reports.