Skip to content

LTX 2.5 / Text to video

LTX 2.5 cinematic establishing shots: a practical recipe

An establishing shot tells the viewer where the scene takes place before asking them to follow an action. For an LTX 2.5 draft, make the location readable and keep the camera movement deliberate. A wide scene packed with tiny moving subjects can be harder to use than a simpler composition.

By JollyAIReviewed 2 min read

Give the location a visual hierarchy

Choose one landmark, a foreground element and a background. A harbour might use a moored boat, the quay and distant hills. Describe how light separates those layers. Avoid adding a crowd unless the crowd is essential to the story; each extra moving element introduces another thing to review.

For a real location, a generated scene is an illustration, not evidence of its actual layout or current condition. Use real footage when factual geography matters.

Generate the shot

  1. Select LTX 2.5 Text to Video in the playground and confirm the available access and preset.
  2. Describe the setting before the camera move.
  3. Ask for one slow movement that reveals the landmark without cutting.
  4. Review straight lines, the horizon and background continuity before adding it to an edit.

Example prompt

PROMPT RECIPE / ADAPT TO YOUR SOURCE

A quiet fictional coastal harbour at sunrise. One small wooden boat in the foreground, a stone quay in the middle distance and blue hills beyond. The camera rises slowly by a modest amount while keeping the horizon level. Warm light, gentle water movement. Sound: soft waves and a distant gull.

Make the opening useful

Leave enough stable footage for a title or narration to begin. If the shot reveals too much too quickly, reduce the camera movement rather than slowing a badly distorted clip in post. Keep the final title as an editable overlay. One readable location cue is usually more useful to the viewer than a long list of decorative cinematic terms.

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.