Génération vidéo avec LTX

# LTX Video Generation

## When to use

Turn an approved text, image, or audio brief into a controlled video-generation plan without handling credentials in the Skill.

## Workflow

1. Confirm the user owns the input or has permission to process it. Collect the source material, audience, output format, and acceptance criteria.
2. Separate observed facts and user-provided constraints from inference. Ask for missing information instead of inventing it.
3. Build a timed beat sheet and shot list before generation or editing. Record narration, captions, transitions, and continuity constraints.
4. Use <skill-tag>skill:820e8b64-9a9c-5c33-8337-ddd348f77f3a</skill-tag> for the connected video workflow. Review the plan before any paid generation or external write.

## Output contract

Return the input assumptions, the approved plan, the generated or analyzed result, uncertainty and limitations, and a concise verification checklist. Preserve source links and provider-returned identifiers when available. Stop if the required connected capability is unavailable; do not substitute local scripts, package installation, or embedded credentials.

## Safety and review

Do not upload private or sensitive media without explicit authorization. Do not claim certainty beyond the evidence. Require review before externally visible, paid, destructive, or account-changing actions.

## Source and license

This Aident-native re-authoring is based on [the pinned upstream source](https://github.com/leoyeai/openclaw-master-skills/tree/e5199b56ae1ff72e141586c17695563486c46702/skills/ltx-video), discovered through [ModelScope](https://modelscope.cn/skills/@leoyeai/ltx-video), and used under MIT. It preserves the upstream workflow goal while removing local executable, credential, and package assumptions.