社交媒体帖子 - Forced Perspective Chibi Pants Pull Portrait
Prompt previewFull prompt
Original author textThis public page preserves the author's original prompt. Review the preview and any published evaluation, then copy the text or open it as a draft. Choose the model, references and current cost in the creation workspace before generating.
Create an ultra-realistic forced-perspective optical illusion portrait in a clean minimalist studio with a seamless warm light-gray background. Show {argument name="main character" default="a beautiful young woman with long dark brown hair"} walking confidently toward the right, looking slightly to her left with a calm expression, holding {argument name="drink" default="a transparent plastic cup of iced coffee"} in one hand. She wears {argument name="outerwear" default="an oversized light gray bomber jacket layered over a dark charcoal hoodie"}, very baggy light-wash denim cargo jeans, and gray-and-white sneakers. Use forced perspective so the denim fabric of one pant leg stretches dramatically backward, as if being pulled. Behind her, include exactly 1 tiny chibi-style mini version of the same woman, angry and determined, gripping the stretched pant leg with both hands and leaning back while pulling; the chibi has long brown hair, an exaggerated frowning face, a small gray jacket, dark hoodie, baggy jeans, and sneakers. Add exactly 7 simple black hand-drawn manga doodle accents around the figures: 2 sparkle clusters near the main woman, 1 sweat/concern mark near her head, 2 puffs of steam near the chibi, 1 set of pull-motion lines near the stretched pants, and 1 curved foot-motion mark near the front shoe. The image should blend photorealistic fashion photography for the main woman with a polished cartoon chibi character, sharp full-body composition, soft studio lighting, subtle floor shadow, editorial realism, no text, no watermark, vertical 2:3 aspect ratio.
Adjust the model, settings and references before generating.
Use prompt →Prefill first, then confirm generation and the current cost.
GPT evaluation
GPT-6-luna
AI evaluation for creative referenceModel: GPT-6-luna Overall score: 8.8 / 10 Prompt quality: 8.7 / 10 Image quality: 9.1 / 10 Prompt–image alignment: 8.6 / 10 图像首眼冲击力强、主体关系清晰且高度贴合提示词,少量涂鸦数量与指定分组不够精确,整体适合上线。
Community reviews
No creator reviews yet.
View and review →