video-workbench/projects/2026-06-23-在路上/slides/s09/s09-v2-prompt.md

S-09 Slide Prompt V2

Status

• Status: prompt ready for host-native generation.
• Worker: Agent S-09.
• Running mode: prompt and generate.
• Review mode: none; do not write s09-v2-review.md.
• Overwrite allowed: no.

Based On Brief

• Brief: projects/2026-06-23-在路上/slides/s09/s09-v2-brief.md.
• Packet: projects/2026-06-23-在路上/tasks/2026-06-24-character-consistency/session-06/packets/s09-v2-slide-agent-packet.md.
• Target slide: S-09 / s09-v2.
• Slide function: traveler under massive bridge / concrete shadow; Section B pressure begins before the S-10 steel-canyon climax.

Reference Inputs

• Style module: B｜高位观察：系统边缘里的小人物.
• Active style reference: projects/2026-06-23-在路上/intake/imgs/B.高位观察型蓝图.png.
• Common calibration board: projects/2026-06-23-在路上/visual-system/style/style-anchor-board-v1.png.
• Image 1: projects/2026-06-23-在路上/visual-system/characters/character-slice-walk-back-v2-from-anchor.png; role: walking/back silhouette, long dark coat, backpack, body continuity.
• Image 2: projects/2026-06-23-在路上/visual-system/characters/character-slice-walk-side-v2-from-anchor.png; role: walking side posture, stride, coat fall, body profile.
• Generation path note: Image 1 and Image 2 must be loaded as visible-context references before host image generation; local paths alone are traceability, not attachment.

Operation Notes

• First read: massive bridge / overpass / concrete shadow and wet city-edge pressure.
• Second read: small traveler moving under the structure.
• Traveler scale: about 1/10 to 1/6 of the frame.
• Character continuity is silhouette-led: coat length, backpack shape, boots, and walking posture matter; face detail does not.
• Garden/API expected: no.

Advisor / Host-Native Record

• Skill mode command: node C:\Users\wangq\.agents\skills\gpt-image-2\scripts\check-mode.js --json.
• Mode result: B-or-C.
• Recommendation: host-or-advisor.
• Garden mode enabled: false.
• API key present: false.
• Model reported by mode check: gpt-image-2.
• Skill files read:
  • C:\Users\wangq\.agents\skills\gpt-image-2\SKILL.md
  • C:\Users\wangq\.agents\skills\gpt-image-2\references\scenes-and-illustrations\concept-scene.md
• Template adaptation: concept-scene.md foreground / midground / background / lighting structure is used only as scene-organization guidance; final output is photorealistic cinematic documentary road-film still, not illustration, poster, or fantasy key art.
• Project / workflow source files actually read:
  • AGENTS.md
  • docs/workflows/slide-task-orchestration.md
  • docs/workflows/slide-task-templates.md
  • projects/2026-06-23-在路上/slides/s09/s09-v2-brief.md
  • projects/2026-06-23-在路上/tasks/2026-06-24-character-consistency/session-06/packets/s09-v2-slide-agent-packet.md
  • projects/2026-06-23-在路上/project.md
  • projects/2026-06-23-在路上/execution-plan.md
  • projects/2026-06-23-在路上/slides/slides.md
  • projects/2026-06-23-在路上/visual-system/style/style-prompt-master.md
  • projects/2026-06-23-在路上/visual-system/characters/character-reference-registry.md

Final Prompt

Create a 16:9 photorealistic cinematic documentary road-film still.

Use Image 1 and Image 2 as visible character continuity references, but keep the traveler small and secondary. Preserve the same road-worn walking silhouette: long dark weathered coat, backpack, boots, slight forward movement, body proportions, and walking posture. Do not emphasize the face.

The image must read first as a cold city-edge system-pressure environment: a massive concrete bridge or overpass overhead, heavy structural beams, underpass shadow, retaining walls, drain lines, wet gray ground, puddles, stains, rust traces, water marks, and hard urban-edge texture. The built structure is much larger than the person and visually presses down on the frame.

Composition: high-angle or distant observational framing, horizontal 16:9. Put the traveler in the lower frame or side area, walking under or along the concrete shadow. The traveler should occupy about one tenth to one sixth of the frame. Environment first, bridge and shadow second, traveler third. The scene should feel like pressure beginning, not the full steel-canyon climax.

Lighting and color: cold gray concrete shadow, wet blue-gray ground reflections, dark khaki and coal-black clothing, low saturation, weak pale sky or soft reflected ambient light only. Documentary grit, real texture, restrained poetic realism, no glamour.

Camera and rendering: cinematic road-film still, realistic lens, natural atmospheric haze, deep spatial scale, high-detail concrete texture, wet surfaces, subtle motion-read in the walking pose, no staged hero pose.

Negative / Avoid

Avoid clean CBD promotion, glossy glass-tower advertisement, futuristic UI, code, holograms, cyberpunk, neon, sci-fi city, commercial skyline as main subject, heroic centered traveler, fashion city portrait, readable text, labels, logos, watermarks, tourism mood, motivational poster tone, victory pose, warm sunrise, broad sunset, high saturation, fantasy magic, or any face-focused portrait treatment.

Output Intent

• Output file: projects/2026-06-23-在路上/slides/s09/s09-v2-image.png.
• Intended use: production still for S-09 in the 在路上 MV slide sequence.
• Review file: intentionally absent by packet rule.