6.1 KiB

Raw Blame History

S-08 Slide Prompt V2

Status

Status: ready for host-native generation.
Slide: S-08
Version: s08-v2
Running mode: prompt and generate
Review mode: none; do not write s08-v2-review.md.
Overwrite allowed: no.

Based On Brief

Brief: projects/2026-06-23-在路上/slides/s08/s08-v2-brief.md
Packet: projects/2026-06-23-在路上/tasks/2026-06-24-character-consistency/session-06/packets/s08-v2-slide-agent-packet.md
Slide function: mud on old boot sole and dragging footstep; body cost connected to road texture.

Reference Inputs

Style module: character detail with road texture; inherit global style kernel plus Module A road/mud texture language.
Active style reference: projects/2026-06-23-在路上/intake/imgs/A.风景主导型蓝图.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-anchor-v2-codex-posture-test.png
- Role: master identity / clothing / prop / boot continuity reference.
Image 2: projects/2026-06-23-在路上/visual-system/characters/character-anchor-v2-walk-side-reference-crop-tight.png
- Role: walking side posture, stride, coat movement, backpack placement, and boot profile reference.
Generation path note: Image 1 and Image 2 are loaded into visible task context before host-native image generation. Local paths are traceability records only.

Operation Notes

Task type: text-to-image generation using visible reference images.
Final image target: projects/2026-06-23-在路上/slides/s08/s08-v2-image.png
First-read order: wet mud / old boot sole / dragging footprint first; fatigue and continued movement second; cropped coat/backpack/body trace only if needed.
Scale: low ground close or medium-close; boot and mud dominate; upper body remains cropped and secondary.
Garden/API expected: no.

Advisor / Host-Native Record

gpt-image-2 mode command: node C:\Users\wangq\.agents\skills\gpt-image-2\scripts\check-mode.js --json
Mode result:

{
  "mode": "B-or-C",
  "recommendation": "host-or-advisor",
  "garden_mode_enabled": false,
  "has_api_key": false,
  "base_url": "https://api.openai.com/v1",
  "model": "gpt-image-2",
  "env_flag_value": "(unset)"
}

Skill file read: C:\Users\wangq\.agents\skills\gpt-image-2\SKILL.md
Template/reference path read: C:\Users\wangq\.agents\skills\gpt-image-2\references\scenes-and-illustrations\concept-scene.md
Template adaptation: use concept-scene foreground / midground / background / lighting structure, but render as photorealistic cinematic documentary road-film still, not illustration, concept art, poster, or key art.

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/s08/s08-v2-brief.md
projects/2026-06-23-在路上/tasks/2026-06-24-character-consistency/session-06/packets/s08-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
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

Final Prompt

Use Image 1 as the master continuity reference for the same road-worn 50-year-old male traveler: dark long worn coat, dark layered clothes, weathered backpack, rugged old brown-black hiking boots, road dust and mud, non-fashion documentary presence. Use Image 2 as the walking side posture reference: side stride, coat movement, backpack position, leg rhythm, and boot profile. Preserve boot/body/coat/backpack continuity from these references, but do not make the face important.

Create a 16:9 photorealistic cinematic documentary road-film still. Low ground close or medium-close camera, near wet muddy road surface. The first read must be wet mud, old boot sole, smeared dragging footstep, grit, stones, and rough road texture. One worn boot is in the foreground or lower-mid foreground, its tread and sole dark with wet mud, dragging through the mud and leaving a heavy smeared footprint. The step should imply fatigue and continued movement, not collapse. A cropped lower leg, coat hem, and small trace of backpack/body may enter the frame only as secondary continuity cues.

World and road texture before person. Real documentary texture with restrained poetic realism. Cold overcast or early gray light. Low saturation palette: cold gray, earth brown, dark khaki, coal black, wet dark blue-gray. Mud should be tactile, uneven, heavy, and wet; include small stones, old ruts, smeared footprint edges, boot tread pressure, and dirty water sheen. The boot must look used and road-worn, consistent with the reference boots, not polished or styled.

Composition: camera almost at mud level, shallow but natural documentary depth of field, boot and mud dominate the frame, dragging footprint leads diagonally into the road. The traveler is cropped and secondary; no face emphasis, no portrait, no heroic centered stance. Keep the image as a film still from a restrained road documentary, not a product shot.

Negative / Avoid

No shoe advertisement, no clean product close-up, no fashion footwear, no sneaker aesthetic, no polished studio lighting, no commercial boot catalog composition, no heroic stride, no face emphasis, no portrait MV, no travel advertising, no motivational poster, no clean scenic tourism, no cyberpunk, no neon, no sci-fi UI, no readable text, no labels, no logos, no watermark, no gore, no injury focus, no collapse, no misery exploitation.

Output Intent

Output file: projects/2026-06-23-在路上/slides/s08/s08-v2-image.png
Intended use: S-08 MV slide image asset.
Acceptance target: mud / old boot sole / dragging footstep reads first; boot/body/coat continuity follows Image 1 and Image 2; no review file is written.

6.1 KiB Raw Blame History