Begin with the output requirements
If generated audio is part of the brief, the current LTX workflow is a relevant starting point. The Wan showcase used on JollyAI is silent, so plan a separate soundtrack for that workflow unless the current interface explicitly offers another option. For either model, source fidelity and motion quality still need review.
Input requirements also matter. Use the appropriate image-to-video mode when an approved starting image is essential. Use text-to-video for exploration. Compare outputs at comparable settings rather than judging a small draft against a larger showcase.
Run a fair practical comparison
- Choose three representative shots from the actual project.
- Keep the creative brief, source image where applicable and target framing consistent.
- Record output metadata, waiting time, processing time if available and failures.
- Score usable motion, subject accuracy and editing effort before selecting a workflow.
Use an acceptance sheet
For a product clip, note whether the outline, material and label remain stable. For B-roll, judge relevance to the narration and whether the camera movement offers a clean edit point. Record why a take was rejected so the comparison includes retry costs.
Make a scoped decision
It is reasonable to choose different models for different shots. Keep the colour treatment and edit style consistent so the finished piece feels coherent. This guide makes no numerical speed or quality ranking: a useful comparison requires matched local measurements, not a mixture of differently configured promotional examples.
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.
- LTX 2.5 upstream project and model information ↗
- LTX 2.5 tool overview on JollyAI
- JollyAI content policy and service terms
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.