Skip to content

LTX 2.5 / Text to video

LTX 2.5 portrait Shorts: storyboard before generating

A portrait Short needs a clear centre of attention and an edit that supports the narration or hook. LTX 2.5 can supply individual visual beats; it does not replace the decisions about pacing, captions and what the viewer should learn.

By JollyAIReviewed 2 min read

Plan the frame and the beat

Write one sentence describing the purpose of each shot. For a craft video, an establishing view of a workspace, a material close-up and a finished object reveal are separate beats. Avoid asking one short generation to cover the entire process.

Choose portrait framing in the available controls and leave space around the subject. Keep essential text outside the generation prompt so it can be added and corrected later. The platform interface may cover parts of the frame, so preview the final edit in context.

Create a short sequence

  1. Draft the voiceover or key message first.
  2. Turn it into a small shot list with one action per clip.
  3. Generate each LTX shot with consistent light and colour descriptions.
  4. Assemble, caption and review the sequence on a phone.

Example shot prompt

PROMPT RECIPE / ADAPT TO YOUR SOURCE

Portrait composition of an original handmade ceramic vase on a simple workbench. A slow camera push reveals the glazed texture while the vase remains stationary. Warm side light, uncluttered background, one continuous shot. Sound: quiet studio ambience.

Improve the edit before generating more

If the Short feels slow, tighten the opening and remove repeated shots. More generated footage will not necessarily improve the story. If the subject is cropped during motion, revise the composition with more space instead of adding longer captions that obscure the problem. Keep factual claims in the script grounded in what you can verify, especially when an AI illustration resembles a real demonstration.

REVIEWED JOLLYAI IMPLEMENTATION

The workflow behind the guide

Written shot → text encoding → configured LTX 2.5 generation graph → video/audio decoding → combined file.

Inputs, presets & access
PRO. Select a duration/quality preset in the playground; output properties depend on that preset and the serving graph.
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 Text 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.

KEEP BUILDING

Continue the workflow.