OpenZhenZhen AI 提示词画廊 · gpt-image-2.5 · image

成年画家自画像破纸跃出的3D错视画

3D Trompe-l'Oeil of an Adult Painter's Self-Portrait Leaping from Torn Paper

成年男性的石墨自画像在阳光充足的画室中从速写本破纸跃出，前景持笔的创作者之手与立体角色构成超现实的自我创作场景. A reusable image recipe made with gpt-image-2.5; explore the prompt and related works in the gallery.

成年画家自画像破纸跃出的3D错视画 — AI image creation
成年画家自画像破纸跃出的3D错视画

提示词 / Prompt

中文提示词

使用已配置的ref-10a-v1身份参考呈现这位明确成年的男性画家及其立体自画像。创作一幅电影感、超写实的3D错视插画，场景位于阳光充足的艺术家画室。一本打开的速写本放在磨损且木纹清晰的书桌上，纸页上画着同一位成年男性的精细石墨素描；素描逐渐转成立体人物，从真实撕裂、边缘参差的纸面中跃出。人物面部与身份忠实于ref-10a-v1。保留来源造型：凌乱棕发、绿色连帽衫和蓝色牛仔裤，但若与配置身份冲突则以身份参考为准。 立体人物的一只手抓住撕裂纸边，另一条手臂自然放在纸页外的桌面上，手掌朝下。他带着惊讶与好奇向外望。前景中出现同一位成年画家的真实手部，握着传统黄色木铅笔，石墨笔尖靠近素描，仿佛刚画完人物跃出的那一部分。桌面散落少量铅笔屑、一块大白色橡皮擦、画笔和小罐子。背景大窗透入暖光，营造纵深与温馨氛围。重点表现纸纤维、石墨、木纹和自然皮肤细节的触感；错视效果清楚，解剖结构可信，纸面与3D人物过渡自然。不要文字、标志或水印。

English prompt

Use configured identity reference ref-10a-v1 for the clearly adult male artist and his dimensional self-portrait. Create one cinematic, hyper-realistic 3D trompe-l'oeil illustration in a sunlit artist's studio. An open sketchbook rests on a worn wooden desk with rich visible grain. Its page shows a detailed graphite pencil drawing of the same clearly adult man; the drawing transitions into a dimensional figure that bursts through realistically torn, jagged paper. Keep the figure's face and identity faithful to ref-10a-v1. Preserve the source styling: messy brown hair, a green hooded sweater and blue jeans only where compatible with the configured identity. One of the figure's 3D hands grips the torn paper edge; his other arm rests naturally outside the page on the desk, palm down. He looks outward with surprised wonder. In the foreground, show the same adult artist's realistic hand holding a traditional yellow wooden pencil, its graphite tip near the sketch as if finishing the form from which the self-portrait springs to life. Scatter a few pencil shavings, one large white eraser, paintbrushes and jars across the desk. Warm window light from the background adds depth and atmosphere. Emphasize tactile paper fibers, graphite, wood grain and natural skin detail. Keep the illusion readable, anatomy plausible, and the page/3D transition clean. No text, logos or watermark.

查看 API 模型

探索更多图片和视频提示词 · 生成图片 · 生成视频 · 在 AI 画布中创作