图像生成案例图

Art direction: polished campaign finish with layered depth cues.  [CORE TASK] Transform the provided input image into a pose-and-light analysis sheet.  This is a white-line rough mannequin conversion. This is NOT a finished character illustration. visualize likely light direction 6. preserve head-torso relationship 5. show illuminated areas with readable green intensity variation   finished person, adorable girl, finely rendered face, hair rendering, clothing rendering, weapon emphasis, striking anatomy preserve camera angle 3. [PRIMARY GOAL] Extract and visualize only: - pose structure - body balance - camera angle - body line flow - inferred light source placement - illuminated areas and light intensity  [INPUT ROLE] Use the provided image as the strict anchor for: - pose - camera angle - body tilt - weight distribution - approximate light design situation  Do NOT preserve: - face rendering - hairstyle rendering - clothing detail - accessories - weapon detail - background architecture - ……

vertical 2:3 · 1024×1536

图像生成案例图（其他场景）：GPT-Image-2 提示词，风格 UI/Realistic/Illustration，竖版 2:3。展示图由 Agnes 按本条提示词改写版生成。

STRICTLY FORBIDDEN: watermark, signature, logo, caption text, distorted anatomy, extra fingers, gibberish letters, blurry faces.