render-3d-character-explainer

render-3d-character-explainer

The free, deterministic renderer for the 3d-character-explainer video ad format — the glossy Pixar-style 3D spot built on an "N types of X" listicle spine, where a recurring human protagonist plus a locked cast of N persona characters (one per list item) carry a hook → "deeper story" → cast-reveal → one beat per list item → kicker → product test → relieved payoff. This capability is the FREE assembly stage only. All generative work (Nano-Banana cast anchors + per-scene keyframes, Kling-V3 i2v clips, ElevenLabs VO + music, or a source ad's audio reused verbatim) happens upstream in the recipe and is handed to this capability as files.

It ports the validated compose recipe from the Bristle "Six Types" restyle run (_render_full.sh — per-scene trim → normalize 1080×1920/fps30 → concat -c copy → mux the source audio, with a static-still fallback on any failed clip). The assembly is deterministic — iterate the cut for free, re-roll only the offending paid beat.

Two modes

• Restyle mode (audio_mode: "restyle", the reference run) — re-tell a finished source ad, beat for beat, as 3D character comedy. The source ad's audio mix (VO + music bed) is reused VERBATIM (source_audio), and the per-scene target_sec table is inherited from the source's scene timing. No new VO or music is rendered. The trims must sum to the source audio length.
• Original mode (audio_mode: "original") — the ad authors its own narration. Each scene carries a measured VO cue (scenes[].vo, target_sec = the ffprobe'd VO duration) which is concatenated into a VO track (loudnorm I=-14) and optionally mixed under a music_bed (loudnorm I=-26 then volume, amix normalize=0).

What it does (the deterministic recipe)

1. Per-scene retime. Each i2v clip is trimmed to its scene target_sec and normalized to identical dims/fps/SAR (scale=W:H:force_original_aspect_ratio=decrease,pad=W:H:(ow-iw)/2:(oh-ih)/2:color=<pad>,fps=30,setsar=1). A clip shorter than its window is extended with tpad=stop_mode=clone; a longer one is -t trimmed. Decrease+pad (never crop) preserves the full 9:16 keyframe framing.
2. Static-still fallback. For any scene whose clip is missing or failed to render, the scene's keyframe PNG is looped (-loop 1) for target_sec, so the master always assembles. Fallback scenes are printed at the end.
3. Identical re-encode + concat. Every segment is re-encoded libx264 -crf 18 -pix_fmt yuv420p -r 30 even if already correct — a dims/framerate mismatch makes the concat demuxer silently drop frames — then concatenated via the concat demuxer (-c copy).
4. Audio. Restyle: source_audio muxed verbatim (-map 0:v -map 1:a), clamped to the video length. Original: per-scene VO track (optional atempo, apad, -t clamp) → loudnorm → optionally mixed under the music bed.
5. Captions last. make_captions.py emits a libass .ass (one cue per scene, start = scene_start + 0.08s, suppressed on any scene with no caption — e.g. a product/end-card beat carrying its own typeset copy). compose.py burns it as the final filter so captions sit on top. Word-level energy-pop captions (Whisper on the narration) are the recipe's upstream option — produce that .ass externally and point captions_ass at it; compose burns whatever .ass it's handed.