# Local Cinematic Highlight PoC — Plan & Milestones

Owner: (Jaden) · Started: 2026-07-21 · Machine: Intel Mac (x86_64, 16 CPU, 32 GB, no GPU)

## Objective

Produce ONE genuinely cinematic highlight from a local source video, end-to-end through the existing
pipeline, using only local models resident in the service runtime:
Piper (voiceover) + MusicGen (music) + AudioLDM2 (SFX), with deliberate visual treatment and pacing,
and explicit human approval before any render.

A valid MP4 or a passing test is NOT success. Success = representative output passes measured media QA
and a human creative review.

## Non-negotiables (still in force during the PoC)

No external AI services in the media path · no placeholder silence/tones/OS `say` as a finished asset ·
no unlicensed assets · no rendering without explicit approval for the specific project · no inference-time
network (models load from local dirs, `HF_HUB_OFFLINE=1`). NOTE: the user authorized model DOWNLOADS on
2026-07-21 (one-time provisioning), reversing the earlier no-download stance; inference stays offline.

## Proven capability baseline (2026-07-21)

| Model | Runtime | Status | Evidence |
|---|---|---|---|
| Piper `en_US-lessac-medium` | piper-tts 1.5.0 | ✅ works | real speech, 22.05 kHz |
| MusicGen `musicgen-small` | transformers 4.44.2 + torch 2.2.2 | ✅ works | 5 s / 44.7 s CPU, mean −18 dB, 32 kHz |
| AudioLDM2 `cvssp/audioldm2` | diffusers 0.30.3 | ✅ works | 3 s / 22.3 s CPU, mean −21.8 dB, 16 kHz |

Environment traps (see memory `local-model-runtime-intel-mac`): torch capped at 2.2.2 (Intel-Mac),
numpy<2, transformers must be 4.x, audiocraft/xformers unusable here, `HF_HUB_DISABLE_XET=1` for downloads.

## Plan

### Phase 1 — Generate all three assets THROUGH the pipeline
- [x] 1.1 Rewrite `tools/local_asset_worker.py`: music→transformers MusicGen, sfx→diffusers AudioLDM2
      (resample to 48 kHz mono), voiceover→Piper (unchanged). audiocraft path removed. CLI + exit codes preserved.
- [x] 1.2 Materialize models into stable `models/` dirs via `save_pretrained` (`tools/provision_local_models.py`):
      `models/musicgen-small` (2.2 G), `models/audioldm2` (4.2 G); `models/piper` (60 M) already present.
- [x] 1.3 License/provenance `.license.txt` sidecars for each model marker file (config.json / model_index.json /
      voice .onnx). BOTH audio models are NON-COMMERCIAL (MusicGen CC-BY-NC-4.0, AudioLDM2 CC-BY-NC-SA-4.0) —
      flagged for production review. Honors the `AssetLicensePolicy` regular-file gate; no Java change.
- [x] 1.4 Smoke test: voiceover 3.67 s/−15.8 dB, music 4.94 s/−12.0 dB, sfx 3.00 s/−20.6 dB — all 48 kHz mono,
      real signal, exit 0.
- [x] 1.5 `mvn -o verify` → 245 tests / 62 classes / 0 failures / 0 errors / 0 skips (unchanged from baseline).

**Phase 1 COMPLETE (2026-07-21).**

### Phase 2 — One approved end-to-end highlight (STOP before render for explicit approval)
- [x] 2.1 Opt-in `localpoc` Spring profile added (`application-localpoc.yml`): venv python, model paths,
      offline, no bootstrap auto-start, heuristic visual, isolated PoC I/O dirs, render OFF, approval REQUIRED.
- [x] 2.2 DJI source processed under `localpoc` (app started, ~4 min 4K analysis): wrote `category.json`
      (GENERIC_VLOG, conf 0.25) + `highlight-candidates.json` (3 windows: 27-39 s, 36-48 s, 81-93 s).
      Actual footage = blue Porsche Taycan aerial orbit (EV car reveal).
- [x] 2.3 Hand-authored `director/edit-plan.json`: 3 x 9 s highlights (opening_hook / rising_energy /
      hero_payoff), grounded in the visible car; passes ALL validator constraints (containment, speed 1.0,
      duration bounds, VO budget, category match). Manual + local-only (no external AI).
- [x] 2.4 **RENDERED (operator-approved 2026-07-21).** render-enabled override + approved.flag → local models
      generated 3 VO (Piper) + 3 music (MusicGen) + SFX (AudioLDM2) → 3 highlights rendered → project
      `final.mp4` assembled (27.3 s, 51.7 MB). Flow ~8.6 min. All real local-model assets, no placeholders.
- [~] 2.5 QA measured (honest):
      **PASS** — 1920x1080 / H.264 / 30 fps / AAC 48 kHz; duration 27.3 s; integrated loudness -15.8 LUFS
      (target -16 ±1); no black frames; no long silence; overlays render & are grounded ("First light.",
      "Silent power."); VO intelligible.
      **FAIL/weak** — true peak: highlight_001 = 0.0 dBFS (clips; target ≤ -1.5 dBTP); h2/h3 = -1.4 dBFS
      (loudnorm TP limiting not enforced tightly). Visual "treatment" is essentially PASSTHROUGH — no visible
      cinematic grade/reframe (renderer maps any treatment to a generic look); overlays are plain white
      captions. LRA 16.9 (high). Pipeline's own qa-report passed because its grade/clip checks are structural.
      **Verdict: genuine end-to-end local PoC, NOT yet "genuinely cinematic."** Visual grade + true-peak
      limiting are the top Phase 3 items.

### Phase 3 — Iterate to quality
Ranked from the first render's evidence:
- [~] P3.1 Stronger filmic grade in `HighlightFfmpegRenderer.cinematicVisualFilter`: S-curve (curves
      medium_contrast) + teal-orange colorbalance + eq + unsharp + vignette (replaces the weak fixed eq).
      Verified visually (richer blue, warm highlights, contrast, vignette). NOTE: still ONE uniform look —
      not yet beat/category-specific (that needs a validated grade enum plumbed via EditDecision). Only the
      highlight renderer changed; multi-clip FfmpegEditRenderer untouched.
- [x] P3.2 True-peak safety: added `alimiter=level=disabled:limit=0.72` after loudnorm in the audio mix.
      VERIFIED by re-render: project true peak 0.0 dBFS (clipping) → **-1.7 dBFS**; per-highlight -1.7/-2.7/
      -2.8 (all <= -1.5 dBTP gate); integrated loudness -16.3 LUFS. (First pass at limit=0.79 gave -1.3 on
      h1, 0.2 dB over — tightened to 0.72 for inter-sample margin.) Test added.
- [ ] P3.3 Overlay styling: premium type, safe-area, subtle animation instead of plain white captions.
- [ ] P3.4 Real CV visual analysis (resident model, no bootstrap script) to improve candidate selection.
- [ ] P3.5 Music/SFX creative fit + ducking review; consider longer inference / better prompts.
- [ ] P3.6 Freeze acceptance thresholds + blinded human creative review vs baseline before declaring success.

## Milestone log
- 2026-07-21: Models provisioned & individually proven (Piper, MusicGen, AudioLDM2). Plan approved. Phase 1 started.
- 2026-07-21: **Phase 1 complete.** Worker rewritten (audiocraft→transformers MusicGen + diffusers AudioLDM2),
  models materialized to `models/` with license sidecars, all 3 asset kinds generate 48 kHz mono real audio
  through the worker, `mvn -o verify` green (245/0/0/0). Paused for review before Phase 2.
- 2026-07-21: Phase 1 committed (a95d1fa). **Phase 2 up to approval gate:** localpoc profile added, DJI source
  processed → candidates + category, grounded 3-highlight director plan authored & pre-validated.
  STOPPED — awaiting explicit render approval for dji_21230510013241_0091_d.

## Deferred (until output-quality gate passes)
Production hardening: Spring Security/OIDC, PostgreSQL/Testcontainers, containers/K8s, CI/CD, distributed
ops, digest-bound authenticated approval. Recorded, not deleted.