Automatic Cartoon Video Lab
New script in → automatic scene analysis → permanent character poses → clean visual timeline export. No recurring character-image uploads. Zero paid APIs by default.
1. Script input
2. Master G character library
Character reference sheets are stored in the project. Vision API inspects the five permanent reference sheets; Master G validates every selected pose. No manual per-episode image uploads.
3. Automatic scene timeline 0 scenes · 0 sec
4. Preview and export
Export records the rendered visual timeline. Keep this page open while exporting. This phase exports clean visuals without script text. Raw dialogue voice uses Kalpa TTS through /api/voice. Pilot mode renders only AR-C001 and prevents stale async scene draws from leaving duplicate character images on the canvas. Kalpa dialogue is embedded in the exported WebM for AR-C001 scenes. Art remains pose-card based: true rigged limb animation and phoneme-accurate lip-sync still require separate transparent body/mouth assets. Background music/SFX and MP4 are not included.
- Scene count comes from the script; no fixed three-scene limit.
- Each scene keeps its intended duration; when a target duration is set, durations are adjusted proportionally to match it.
- Master G validates character IDs and the brain only selects pose IDs from the permanent catalog.
- Kilo free model is optional for shot/pose selection; local fallback keeps the app usable if the free model is unavailable.