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
Ready. Choose a saved script or generate a new one.
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.
Loading permanent character library…
3. Automatic scene timeline 0 scenes · 0 sec
Load a script to build the timeline.
4. Preview and export
Ready.
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. Basic speaking/body/hand motion is preview-only; audio is not yet embedded in exported video. Character-specific voices, detailed lip-sync, original music/SFX and mobile-compatible MP4 come in later steps.
- 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.