GPT Image 2 on ChatGPT

GPT Image 2 on ChatGPT Upload one reference image before generating. MAIN PROMPT Create a finished editorial character poster inspired by the uploaded reference image. Preserve the recognizable identity, hairstyle, clothing details, pose, and important visual characteristics of the subject while translating them into a sophisticated flat geometric illustration. FORMAT LOCK Vertical 3:4 composition. Edge-to-edge warm off-white paper background. One standalone poster. Clean editorial layout. CHARACTER One adult character constructed from a few oversized asymmetric geometric shapes. Slightly exaggerated proportions, small head, elongated capsule-like limbs, simple mitten-style hands, and one oversized object integrated naturally into the pose and silhouette. Preserve the subject's recognizable appearance while simplifying details into graphic shapes. STYLE Flat geometric illustration, asymmetric proportions, crisp color blocks, soft airbrushed shading, subtle dark-to-color spray gradients where shapes overlap, fine print grain, delicate stippling mostly inside darker areas, refined contemporary editorial poster aesthetic. FACE & EXPRESSION Minimal black cut-paper facial features: simple crescent eyes and minimal mouth. The emotion should be communicated primarily through the character's full-body gesture and silhouette rather than detailed facial expression. PALETTE Warm off-white #F3F1EB, near-black ⁠10100F, hot pink #F553D2, warm red #F42726, cobalt ⁠293EA1, emerald ⁠13785D. Keep colors flat and graphic with controlled soft gradients only where forms overlap. TEXT Add one short caption in small bold black uppercase sans-serif inside an open paper pocket. Caption: "[MAIN_TEXT]". No other text, logos, labels, or typography. CUSTOMIZATION Character & Object: [WHO + THE OVERSIZED THING] Gesture & Emotion: [POSE + FEELING] Shape Idea: [HOW BODY AND OBJECT FORM THE SILHOUETTE] COMPOSITION Keep the character and oversized object as the main visual focus. Use generous negative space and a balanced editorial arrangement. The object should visibly affect the overall silhouette and feel integrated into the character's pose. NEGATIVE PROMPT No extra text, logos, outlined cartoon style, glossy 3D, realistic skin, photorealism, coarse canvas texture, busy background, extra limbs, distorted anatomy, excessive facial detail, photorealistic shading, random objects, clutter, watermark.

GPT Image 2 on ChatGPT 在生成之前上传一张参考图。 MAIN PROMPT 创建一张完成的编辑风格人物海报，灵感来自上传的参考图。在将主体转化为精致的扁平几何插画时，保留可识别的人物身份、发型、服装细节、姿势以及重要的视觉特征。 FORMAT LOCK 竖版 3:4 构图。边缘到边缘的暖调米白色纸张背景。独立的一张海报。简洁的编辑式版面。 CHARACTER 一个成年人角色，由几个超大的不对称几何形状构成。比例略微夸张，小头，拉长的胶囊状四肢，简单的连指手套式手部，以及一件超大物件自然融入姿势和轮廓中。在简化为图形形状的同时，保留主体可识别的外观。 STYLE 扁平几何插画，不对称比例，清晰的色块，柔和的喷枪阴影，在形状重叠处使用细腻的由深至彩色喷涂渐变，细腻的印刷颗粒，主要在较深区域内进行精致的点描，精致现代的编辑海报美学。 FACE & EXPRESSION 极简的黑色剪纸式面部特征：简单的月牙形眼睛和极简的嘴部。情感应主要通过角色的全身姿态和轮廓来传达，而非细致的面部表情。 PALETTE 暖米白 #F3F1EB，近黑 ⁠10100F，亮粉色 #F553D2，暖红 #F42726，钴蓝 ⁠293EA1，翠绿 ⁠13785D。保持颜色扁平、图形化，仅在形状重叠处使用受控的柔和渐变。 TEXT 在一个打开的纸袋内添加一条简短的说明文字，使用小号粗体黑色大写无衬线字体。说明文字："[MAIN_TEXT]"。不添加其他文字、标志、标签或排版。 CUSTOMIZATION Character & Object: [WHO + THE OVERSIZED THING] Gesture & Emotion: [POSE + FEELING] Shape Idea: [HOW BODY AND OBJECT FORM THE SILHOUETTE] COMPOSITION 将角色和超大物件作为主要视觉焦点。使用充裕的负空间和均衡的编辑式排布。物件应明显影响整体轮廓，并感觉与角色的姿势融为一体。 NEGATIVE PROMPT 不要出现额外的文字、标志、描边卡通风格、闪亮 3D、写实皮肤、照片写实主义、粗糙画布纹理、繁杂背景、多余肢体、扭曲的解剖结构、过多面部细节、照片级真实感阴影、随机物件、杂乱、水印。