4×4 动作分解参考表
Full Prompt
[STYLE] Monochrome grayscale illustration, 3D-rendered character, clean instructional reference sheet, white background, comic-style cell grid layout, technical diagram aesthetic. [LAYOUT] 4×4 grid layout with a total of 16 panels. Each panel is separated by thin black border lines. Cells are numbered from 1 to 16, with consistent panel sizes. [CHARACTER] image1 (the same character appears consistently in all panels) [PANEL STRUCTURE – per cell] Top-left: bold number badge + English title text Center: full-body character pose illustration Bottom-left: English description text (3–4 lines) Overlay: directional arrows indicating movement [ARROWS / MOTION INDICATORS] Curved arrows, straight arrows, and circular rotation indicators placed around the character to show motion flow and direction. [RENDERING STYLE] Highly detailed 3D sculpted style, soft studio lighting, subtle shadows, no color, grayscale shading, clean linework, game concept art quality. [NEGATIVE] No background scenery, no color tones, no additional characters, no complex background.
Full Prompt · #347
-
同一人脸十二款发型 Lookbook
Create a 12-panel grid (3 columns × 4 rows, numbered 1 to 12) showing the SAME person from
#535
-
手绘涂鸦时尚人物插画
Transform the subject from the reference image into a cute, quirky hand-drawn doodle illus
#533
-
实拍背景涂鸦人物替换
Transform ONLY the people in the uploaded photo into adorable hand-drawn doodle characters
#530
-
圣诞街景 Chibi 真实背景人像
Use the uploaded image as the primary reference. Transform the person into a cute, hand-dr
#528
-
儿童故事书手绘头像
Use the single uploaded photo as the only visual reference. Transform the person into an a
#522
-
Brutalist Freestyle 角色设定表
Use the uploaded reference image as the primary character design reference, preserving the
#512
Sources: public cases from the official GPT Image 2 gallery (gpt-image2.canghe.ai); prompts and images are published by the original case authors.
