12 — Media Orchestration
Plan and generate all site media section-by-section: images (GPT Image 1.5), logos (Ideogram v3), video (Sora), OG cards, and compression pipeline.
Model migration note (pass-77, 2026-06-09): DALL-E → GPT Image 1.5 + GPT-4o → GPT Image 2 vision. Per platform.openai.com/docs/deprecations.
Submodules
- media-prompts — prompt templates, Ideogram v3 API
- compression-pipeline — Python code, format tables, CF Image Transforms, CLS, broken image detection
- og-image-generation — Satori edge-rendered OG, KV / R2 cache, meta-tag helper
- image-optimization — Sharp processing, responsive srcset, WebP/AVIF, blur placeholders, R2 pipeline
- image-profiling — GPT Image 2 vision batch profiling
- lightbox-classifier — per-image eligibility:
kind!=logo + ≥1024×768 + score≥7
- social-brand-hex — canonical brand-color map per social platform
- notebooklm-pipeline — per-site podcast via ElevenLabs Studio + infographic via Vega-Lite/Recraft/GPT-Image-2 + HeyGen video + CF Stream + RSS + JSON-LD + cost ceiling $3.50/site
Strategy by Section
Hero → GPT Image 1.5 / Sora · Features → GPT Image 1.5 / SVG · How It Works → GPT Image 1.5 · Testimonials → stock · About → stock/real · Blog → GPT Image 1.5 · Social → Satori OG 1200×630 · Icons → Ideogram v3
Pre-gen checklist: communication goal? Brand style? Dimensions? Format? Budget? Stock or generated?
Visual Inspection (MANDATORY)
Read every image before deploy. Check: blur, artifacts, watermarks, wrong colors, AI hallucinations, gibberish text. Fail = regenerate w/ improved prompt. Quality bar: 2× retina, no artifacts, brand palette, consistent style, no uncanny valley.
Brian's Style
- Space/cosmic —
#00E5FF + #7C3AED, deep black (#060610); connections/dots — quantum, neural, constellation
- "Ultra realistic" scenes; transparent logos; simpler always; motifs — squirrels, turtles
Image Generation
- GPT Image 1.5 preferred (best quality); GPT Image 1 for speed; GPT Image 1-mini for bulk/drafts
- Fallback:
scripts/image_gen.py; product screenshots: Playwright on live URL
- Be specific: include colors, specify avoidances
GPT Image 1.5 First Slot-Fill (CANONICAL — UNIVERSAL)
PRIMARY originator for every slot real-entity sources (Places / uploads / scrape) didn't fill. GPT Image 1.5 invoked BEFORE generic stock; stock APIs run parallel speed-pass fallback (instant return if GPT Image 1.5 hangs >15s). See skill 15 media-acquisition + Fail-CLOSED auto-regenerate (5 attempts, $0.40 worst-case ceiling per slot).
Per-Slot Prompt Mandatory Fields (BUILD-BREAKING — validate-image-prompts.mjs + validate-dalle-slot-fill.mjs)
Every GPT Image 1.5 call MUST encode 6 fields from _media_slots.json:
- Page topic + intent verbatim from
topic_intent
- Brand palette tokens from
_brand.json.colors (inline hex)
- Composition + aspect ratio matching
aspect
- Subject specificity (NEVER "people" — always "octogenarian volunteer plating soup, soft window light, documentary style")
- Photographic technical specs (camera, lens, lighting, DoF — "shot on Hasselblad, 85mm prime, golden hour, shallow DoF")
- Negative prompt block ("no text, no watermarks, no logos, no extra fingers, no AI artifacts, no stock-photo cliches")
Generic prompts FAIL validator. Same template applies to FLUX, Recraft, Stability.
Fail-CLOSED Auto-Regenerate (BUILD-BREAKING — validate-no-empty-slots.mjs)
Every slot MUST end build w/ filled_url != null AND filled_score >= relevance_floor (default 8/10 via GPT Image 2 vision). Failure modes (Pexels empty, NSFW-flagged, broken scrape, vision below floor) → immediate re-gen w/ REFINED prompt — NEVER silent skip, NEVER substitute brand-gradient unless 5 attempts exhausted. media_pipeline_orchestrator sub-agent owns this loop. See media-acquisition.md § Fail-CLOSED chain.
Logo / Icon / Video / OG
- Logo — Ideogram v3 (best text rendering); Icons — Recraft V3; output: PNG transparent + SVG; bg removal → favicon set (16/32/180/192/512 + maskable); brand mark MUST be vector-clean
- Video — Sora (primary cinematic); Veo (narrative stitching, 7-8 × 8-sec clips → 60-sec arc); HeyGen (explainer/spokesperson); captions VTT + transcript;
prefers-reduced-motion → static poster fallback
- OG (1200×630) — Satori edge-rendered, per-route unique, BRANDED CARD never raw photo, ≤100KB, cached KV 7d / R2 forever
Stock Photography + Asset Compression + Performance
Stock: Pexels first (free, API); Pixabay second. Never Unsplash (generic), iStock/Getty (paid). Critique-and-remix loop max 3 rounds; AI vision <7/10 = reject + regenerate.
Compression: AVIF primary (94% browser support, 20-30% smaller than WebP); WebP fallback (Safari 14+); JPEG legacy. Sharp: 320/640/1280/1920w srcset; blur placeholder; dominant color → CSS bg fill. R2 upload per-extension content-type.
Budgets: total images/page ≤500KB; largest single ≤200KB; Hero LCP fetchpriority="high" + preload; loading="lazy" + decoding="async" on all others.
See submodules for: media-prompts, compression-pipeline, og-image-generation, image-optimization, image-profiling, lightbox-classifier, social-brand-hex, notebooklm-pipeline, build-breaking-rules.
1---2name: media-orchestration3description: Section-by-section media planning and generation. Image generation (GPT Image 1.5 primary, built-in fallback), logo/icon generation (Ideogram v3 → favicon set), video generation (Sora), social preview images (OG 1200x630 + AI search optimization), stock photo curation (Pexels, Pixabay), critique/remix loops (max 3 rounds), asset compression pipeline, and media performance budgets.4license: Rutgers5---67# 12 — Media Orchestration89Plan and generate all site media section-by-section: images (GPT Image 1.5), logos (Ideogram v3), video (Sora), OG cards, and compression pipeline.1011> **Model migration note (pass-77, 2026-06-09)**: `DALL-E` → **GPT Image 1.5** + `GPT-4o` → **GPT Image 2 vision**. Per `platform.openai.com/docs/deprecations`.1213## Submodules1415- **media-prompts** — prompt templates, Ideogram v3 API16- **compression-pipeline** — Python code, format tables, CF Image Transforms, CLS, broken image detection17- **og-image-generation** — Satori edge-rendered OG, KV / R2 cache, meta-tag helper18- **image-optimization** — Sharp processing, responsive srcset, WebP/AVIF, blur placeholders, R2 pipeline19- **image-profiling** — GPT Image 2 vision batch profiling20- **lightbox-classifier** — per-image eligibility: `kind!=logo` + ≥1024×768 + score≥721- **social-brand-hex** — canonical brand-color map per social platform22- **notebooklm-pipeline** — per-site podcast via ElevenLabs Studio + infographic via Vega-Lite/Recraft/GPT-Image-2 + HeyGen video + CF Stream + RSS + JSON-LD + cost ceiling $3.50/site2324## Strategy by Section2526Hero → GPT Image 1.5 / Sora · Features → GPT Image 1.5 / SVG · How It Works → GPT Image 1.5 · Testimonials → stock · About → stock/real · Blog → GPT Image 1.5 · Social → Satori OG 1200×630 · Icons → Ideogram v32728Pre-gen checklist: communication goal? Brand style? Dimensions? Format? Budget? Stock or generated?2930## Visual Inspection (MANDATORY)3132Read every image before deploy. Check: blur, artifacts, watermarks, wrong colors, AI hallucinations, gibberish text. Fail = regenerate w/ improved prompt. Quality bar: 2× retina, no artifacts, brand palette, consistent style, no uncanny valley.3334## Brian's Style3536- Space/cosmic — `#00E5FF` + `#7C3AED`, deep black (`#060610`); connections/dots — quantum, neural, constellation37- "Ultra realistic" scenes; transparent logos; simpler always; motifs — squirrels, turtles3839## Image Generation4041- **GPT Image 1.5** preferred (best quality); **GPT Image 1** for speed; **GPT Image 1-mini** for bulk/drafts42- Fallback: `scripts/image_gen.py`; product screenshots: Playwright on live URL43- Be specific: include colors, specify avoidances4445## GPT Image 1.5 First Slot-Fill (CANONICAL — UNIVERSAL)4647PRIMARY originator for every slot real-entity sources (Places / uploads / scrape) didn't fill. GPT Image 1.5 invoked BEFORE generic stock; stock APIs run parallel speed-pass fallback (instant return if GPT Image 1.5 hangs >15s). See skill 15 `media-acquisition` + Fail-CLOSED auto-regenerate (5 attempts, $0.40 worst-case ceiling per slot).4849## Per-Slot Prompt Mandatory Fields (BUILD-BREAKING — `validate-image-prompts.mjs` + `validate-dalle-slot-fill.mjs`)5051Every GPT Image 1.5 call MUST encode 6 fields from `_media_slots.json`:52531. Page topic + intent verbatim from `topic_intent`542. Brand palette tokens from `_brand.json.colors` (inline hex)553. Composition + aspect ratio matching `aspect`564. Subject specificity (NEVER "people" — always "octogenarian volunteer plating soup, soft window light, documentary style")575. Photographic technical specs (camera, lens, lighting, DoF — "shot on Hasselblad, 85mm prime, golden hour, shallow DoF")586. Negative prompt block ("no text, no watermarks, no logos, no extra fingers, no AI artifacts, no stock-photo cliches")5960Generic prompts FAIL validator. Same template applies to FLUX, Recraft, Stability.6162## Fail-CLOSED Auto-Regenerate (BUILD-BREAKING — `validate-no-empty-slots.mjs`)6364Every slot MUST end build w/ `filled_url != null AND filled_score >= relevance_floor` (default 8/10 via GPT Image 2 vision). Failure modes (Pexels empty, NSFW-flagged, broken scrape, vision below floor) → immediate re-gen w/ REFINED prompt — NEVER silent skip, NEVER substitute brand-gradient unless 5 attempts exhausted. `media_pipeline_orchestrator` sub-agent owns this loop. See `media-acquisition.md` § Fail-CLOSED chain.6566## Logo / Icon / Video / OG6768- **Logo** — Ideogram v3 (best text rendering); **Icons** — Recraft V3; output: PNG transparent + SVG; bg removal → favicon set (16/32/180/192/512 + maskable); brand mark MUST be vector-clean69- **Video** — Sora (primary cinematic); Veo (narrative stitching, 7-8 × 8-sec clips → 60-sec arc); HeyGen (explainer/spokesperson); captions VTT + transcript; `prefers-reduced-motion` → static poster fallback70- **OG (1200×630)** — Satori edge-rendered, per-route unique, BRANDED CARD never raw photo, ≤100KB, cached KV 7d / R2 forever7172## Stock Photography + Asset Compression + Performance7374**Stock**: Pexels first (free, API); Pixabay second. Never Unsplash (generic), iStock/Getty (paid). Critique-and-remix loop max 3 rounds; AI vision <7/10 = reject + regenerate.7576**Compression**: AVIF primary (94% browser support, 20-30% smaller than WebP); WebP fallback (Safari 14+); JPEG legacy. Sharp: 320/640/1280/1920w srcset; blur placeholder; dominant color → CSS bg fill. R2 upload per-extension content-type.7778**Budgets**: total images/page ≤500KB; largest single ≤200KB; Hero LCP `fetchpriority="high"` + preload; `loading="lazy"` + `decoding="async"` on all others.7980## See submodules for: media-prompts, compression-pipeline, og-image-generation, image-optimization, image-profiling, lightbox-classifier, social-brand-hex, notebooklm-pipeline, build-breaking-rules.
heymegabyte