Lab / Storyboard Formats / 3×3 Expression Sheet · Torn Paper Circles · Pixar 3D

3×3 Expression Sheet · Torn Paper Circles · Pixar 3D

9-emotion × 9-outfit cross-axis character bible · torn paper circle frames(non-rectangular panel · 新 visual primitive)· Pixar 3D style · enumerative descriptive sub-paradigm · single GPT Image 2 call

Promoted via tools/promote · 2026-05-02. Source probe sidecar: experiments/pixar_expression_sheet_verbatim_v1_20260502/pixar_expression_sheet_verbatim_v1.run.yaml

validated_2plus · ¥0.5 · aspect 1:1 · providers · gpt_image_2 · id · storyboard-3x3-expression-sheet

3×3 Expression Sheet · Torn Paper Circles · Pixar 3D

sample · experiments/pixar_expression_sheet_verbatim_v1_20260502/pixar_expression_sheet_verbatim_v1.png

Run Record

2026-05-02T14:10:19+08:00

✓ pass¥0.571.9s wall· 2.2MB

provider · gpt_image_2 (apimart) · aspect_ratio=1:1 · size=1:1 · n=1

prompt · inline (no library entry · 580 chars)

refs · none (pure T2I)

task_id · task_01KQKMW61NV9P141JT95EG042H

script · tools/probe.py

view full sidecar yaml

date: '2026-05-02T14:10:19+08:00'
result: pass
prompt:
  text: >-
    3D Pixar-style expression sheet, cute stylized avatar with wavy dark hair and round glasses, 3x3
    grid layout, peeking through torn paper circles, emotions: wink, sunglasses cool, thinking,
    happy smile, thumbs up, drinking boba tea, friendly wave, laughing, cute pout, different
    outfits: green sweater, red jacket, yellow hoodie, striped tee, orange shirt, blue top, purple
    vest, pink cardigan, teal pullover. Soft cinematic lighting, clean white background, vibrant
    colors, high detail, adorable cartoon character, playful expressions, consistent character
    design across all poses
refs: []
provider:
  id: gpt_image_2
  relay: apimart
  config:
    aspect_ratio: '1:1'
    size: '1:1'
    'n': 1
output:
  path: ./pixar_expression_sheet_verbatim_v1.png
  bytes: 2270130
  wall_seconds: 71.9
  task_id: task_01KQKMW61NV9P141JT95EG042H
script: tools/probe.py
cost_yuan: 0.5
notes: Probed via tools/probe.py · 2026-05-02 14:10.

Evidence Samples

1 additional sample · stability / variation evidence beyond the canonical above

multi-sample · evidence-based

yuan_kid · Pixar 3D · SPORT visor 9/9 自动 carry-through 验证 wardrobe-as-identity — yuan_kid · Pixar 3D · SPORT visor 9/9 自动 carry-through 验证 wardrobe-as-identity

Probed via tools/probe.py · 2026-05-02 14:10.

2026-05-02 ·59.2s wall · pixar_expression_sheet_yuan_kid_v1.png

✓ pass¥0.559.2s wall· 2.2MB
provider · gpt_image_2 (apimart) · aspect_ratio=1:1 · size=1:1 · n=1
prompt · inline (no library entry · 836 chars)
refs · 1 input
🔒
wide_close_composite_oref.jpg
[28ff0593…]
private · local only
task_id · task_01KQKMW9Z6D7MEDP6BAYN4Y81X
script · tools/probe.py
view full sidecar yaml
date: '2026-05-02T14:10:08+08:00' result: pass prompt: text: >- 3D Pixar-style expression sheet · @yuan_kid (the characteristic Asian kid · faithfully match face / age / proportions from reference image · same hair · same identity), 3x3 grid layout, peeking through torn paper circles, emotions: wink, sunglasses cool, thinking, happy smile, thumbs up, drinking boba tea, friendly wave, laughing, cute pout, different outfits: green sweater, red jacket, yellow hoodie, striped tee, orange shirt, blue top, purple vest, pink cardigan, teal pullover. Soft cinematic lighting, clean white background, vibrant colors, high detail, adorable Pixar 3D character, playful expressions, same face across all 9 poses, consistent character design. Faithfully recreate the character identity from the reference image — same face, same age, same proportions, only style transformed to 3D Pixar-adjacent rendering. refs: - source: personalized-video/ip/yuan_kid/refs/derivatives/wide_close_composite_oref.jpg sha256: 28ff059384a74951b67a46c835f5f763020fd747ab4e1a54190113751d7c0cae upload_url: >- https://personalized-video-refs.tos-cn-beijing.volces.com/28ff059384a7/wide_close_composite_oref.jpg?X-Tos-Algorithm=TOS4-HMAC-SHA256&X-Tos-Credential=AKLTYjM3ZTcxNjI5ZjFkNGZmYjgyMTNjNWRjZjU4N2IzNjY%2F20260502%2Fcn-beijing%2Ftos%2Frequest&X-Tos-Date=20260502T060909Z&X-Tos-Expires=86400&X-Tos-SignedHeaders=host&X-Tos-Signature=27954a8aad2136e53da35ebb19657b826e9987d53188390e7b78c3b4723f41f5 provider: id: gpt_image_2 relay: apimart config: aspect_ratio: '1:1' size: '1:1' 'n': 1 output: path: ./pixar_expression_sheet_yuan_kid_v1.png bytes: 2292041 wall_seconds: 59.2 task_id: task_01KQKMW9Z6D7MEDP6BAYN4Y81X script: tools/probe.py cost_yuan: 0.5 notes: Probed via tools/probe.py · 2026-05-02 14:10.

prompt not yet extracted to library

Verbatim prompt lives in the experiment script. Pending migration to recipes/image_gen/gpt_image_2/prompts/.

Cross-Reference

methodology · — no dedicated recipe doc · referenced in memory only —

axis · §Storyboard Formats · image-layout-end · pre-viz / collage / sheet

Sister capabilities · same axis

validated_2plus

Plot-driven 3-act storyboard · 9 panels · single image · pre-viz for Comic Skit / Narrative MV

12-Panel Rhythm

Mood-driven multi-angle collage · K-pop / fashion / brand reel · feed as i2v ref (¥0.5 collage → ¥3 video)

16-Panel Day-Cycle

Long narrative flat-list · multi-environment + lighting evolution (morning → night) · slice-of-life

2×5 Cinematic Shot List

长 prompt + per-cell shot spec + 风格 anchor (BBC Planet Earth / 影像类) → 10-cell 电影分镜表 · 每 cell 是真电影 shot (景别 / 灯光 / subject behavior 显式 spec) · 接 i2v 出 15s 短片

4×4 Transformation

Single-env + progressive accumulation + typography-as-feature · save-distribution (Pinterest/IG/RED) · GRWM / makeup / cooking

5×5 Style Grid

单 subject + 25 cells × distinct styles · style-axis (vs narrative/rhythm-axis) · style 探索 / 客户教育 / pre-viz · minimal prompt unlock model prior

All-in-One Asset Sheet

observed_external

多元素 1 张图 (主角 + 配角 + 武器 + 战马 + 环境) · 替多次生图 · 风格统一

Storyboard Treatment Ref

observed_external

70% 视觉 + 30% sidebar specs (时间戳 / 相机 / SFX / BGM) · negative-style 引用作 R2V structural ref

Staging Blueprint Ref

observed_external

俯视平面图 + 颜色站位 + 运动轨迹 · 4 ref 分工 · multi-character 站位锚

360° Equirectangular Panorama

4096-class 360 全景 · seamless horizontal wrap · undocumented ApiMart 2:1 aspect

Motion Sheet Recreation

Monochrome 教学 sheet 重画成 color photoreal · 同 layout/numbering/箭头 + character/wardrobe/color 三重替换

Production Bible · 12-Panel + Cast + Props + Location

Full pre-production bible · 12-panel storyboard + cast turnaround + prop sheet + location refs + style refs + palette in one GPT Image 2 call · pre-viz / pitch deliverable

Ring Spectrum Poster · Center + Ring · 9:16 Mobile-First

Center anchor + ring of N same-character variants in continuous immersive space · 9:16 mobile-first viral poster · system prompt + hidden reasoning + audience CTA paradigm (per 岳哥 4-version system)