Thư viện prompt AI OpenZhenZhen · gpt-image-2.5 · image

Người thật tương tác với bóng hình graffiti đen

Real Person Interacting with Black Graffiti Shadow Portrait

Người thật tương tác với bóng hình graffiti đen — khám phá tác phẩm được tạo bằng gpt-image-2.5 trên OpenZhenZhen, kèm prompt gốc và ví dụ tạo nội dung để tham khảo.

Người thật tương tác với bóng hình graffiti đen — AI image creation
Người thật tương tác với bóng hình graffiti đen

Prompt

Prompt tiếng Trung

使用上传参考图作为唯一人物外观参考，精确保留参考人物的面部身份、面部比例、眼睛、鼻子、嘴唇、肤色、发型、发色、可见发饰、服装、造型和整体可识别气质；不要虚构参考图中不存在的外观细节，所有身份、服装、发型和配饰都直接依据参考图。创建一张 4:5 垂直混合风格肖像：参考人物的写实全身或近全身版本站在干净墙边，墙上直接绘制同一人物的黑色手绘涂鸦影子。涂鸦影子只能是黑色素描线稿，不是真实阴影，不是第二个写实人物，也不是全彩动漫角色，但要匹配参考人物的发型轮廓、配饰、服装轮廓和整体身份。真人保持照片级写实、时尚且自然，表情可爱、略显困惑、轻微尴尬而俏皮，像在疑惑自己为什么要和影子做这种事；涂鸦影子则更加夸张、活泼、顽皮和混乱，周围加入漫画动态线、爱心、星星、闪光和喜剧效果。每次生成必须发明一个全新的俏皮姿势，不得重复既有姿势，避免指向、手指枪、重复站立或双方互相指着；真人执行该创意的可信柔和版本，涂鸦影子执行同一创意的夸张卡通版本。可从俏皮偶像姿势、滑稽舞蹈、侧身举臂、巨大爱心、眨眼、双手捧脸、戏剧性亮相、模拟惊讶、原地奔跑、顽皮踮脚、双臂张开、悄悄溜走、可爱捣蛋、夸张反应、搞怪胜利、俏皮平衡、躲猫猫、羞涩顽皮或过度自信中选择并进一步变形成独特动作，不要照抄示例。真人和涂鸦影子周围留出足够空间以看见完整姿势，涂鸦影子高度与真人相近或略高；构图可爱、俏皮、时尚、滑稽、顽皮且适合社交媒体。保持墙面干净、两种风格边界清晰、自然解剖和手指正确；无可读文字、无水印。

Prompt tiếng Anh

Use the uploaded reference image as the only appearance reference for the character. Preserve the reference character's facial identity, facial proportions, eyes, nose, lips, skin tone, hairstyle, hair color, visible hair accessories, outfit, styling, and overall recognizable vibe exactly; do not invent appearance details absent from the reference, and infer identity, clothing, hair, and accessories directly from it. Create a 4:5 vertical mixed-style portrait: a realistic full-body or nearly full-body version of the reference character stands beside a clean wall, with a black hand-drawn doodle shadow of the same character sketched directly onto the wall. The doodle shadow must be black sketch line art only, not a real shadow, not a second realistic person, and not a full-color anime character, while clearly matching the reference hairstyle silhouette, accessories, outfit silhouette, and overall identity. Keep the real character photorealistic, stylish, and naturally posed, with a cute, slightly confused, mildly embarrassed, playful expression as if wondering why she is doing this with her shadow. Make the doodle shadow much more energetic, exaggerated, mischievous, and chaotic, surrounded by manga motion lines, hearts, stars, sparkles, and comic effects. Invent a completely new playful pose for every generation; do not repeat previous poses, pointing gestures, finger guns, repetitive standing poses, or simply having the two figures point at each other. The real character performs a believable softer version of the idea while the doodle shadow performs an over-the-top cartoon version. Choose and further transform a fresh concept such as a playful idol pose, silly dance, sideways lean with one arm overhead, giant heart, cheeky wink, hands near cheeks, dramatic ta-da, mock surprise, running in place, mischievous tiptoe, arms stretched apart, sneaking away, cute troublemaker, dramatic overreaction, goofy victory, playful balance, peekaboo, shy-but-mischievous, or overconfident pose; never copy an example literally. Leave enough space around both figures to show the complete poses, with the doodle shadow about the same height as or slightly taller than the real character. Keep the composition cute, playful, stylish, funny, mischievous, and social-media-friendly. Preserve a clean wall, clear separation between the two visual styles, natural anatomy, and correct fingers; no readable text, no watermark.

Xem mô hình API

Xem thêm prompt hình ảnh và video · Tạo hình ảnh · Tạo video · Tạo trên canvas AI