OpenZhenZhen AI 提示词画廊 · gpt-image-2.5 · image
同一成年男性48格影棚表情接触表
48-Panel Studio Expression Contact Sheet of the Same Adult Male
A single 4:5 white-studio contact sheet with 48 distinct, cleanly separated head-and-shoulders expressions of the same clearly adult man, identity-bound to ref-10a-v1.
提示词 / Prompt
中文提示词
以用户上传的参考图作为主要可见人物的面部身份依据。在不与身份参考冲突的情况下，保留来源的场景、造型、服装、姿势、构图、光线和视觉风格。 创作一张竖幅4:5影棚图像，内部为精确的6列×8行网格，共48个大小相同的人像面板。每格都呈现同一位明确成年男性（25岁以上），保持同一张可辨认的面孔、自然中长深色头发和简洁白衬衫；仅改变面部表情，部分格子可增加一个幅度轻微、自然的手势。所有面板统一为头肩构图、齐眼视角、相同光线、服装和白色无缝背景。格间使用细而均匀的白色间隔，不加外框、标签、编号或文字。 按从左至右、从上至下的顺序安排48种不同表情：第1行——中性、浅笑、开怀微笑、大笑、坏笑、挑眉。第2行——眨眼、惊讶、震惊、睁大眼睛、张口表情、戏剧性倒吸气。第3行——斜视、眯眼、愤怒、皱眉、咬紧牙关、鼓起脸颊。第4行——吐舌、夸张笑容、俏皮假装尖叫、专注凝视、怀疑神情、困惑神情。第5行——疑惑坏笑、顽皮对眼、大笑、假哭、双手捧脸、手指在眼周做望远镜状。第6行——部分遮脸、轻轻拉动嘴角、下巴托拳、欣喜若狂的笑、严肃凝视、平静神情。第7行——收窄眼神、假装沮丧、戏剧性叹息、夸张震惊、滑稽表情、自豪微笑。第8行——讽刺笑、困惑地歪头、自信坏笑、面无表情、放松的结束姿态、轻柔闭眼微笑。确保每种表情都清楚不同，同时保持人体结构可信；避免面部扭曲、眼睛错位或手指重复/缺失。 采用柔和正面影棚人像光与均衡补光，阴影克制，每张脸清晰对焦，人物比例统一，呈现干净的编辑肖像效果。不出现其他人物、道具、文字、标志或水印。
English prompt
Use the uploaded reference image as the facial identity reference for the main visible person. Keep the source scene, styling, clothing, pose, composition, lighting and visual style unless they conflict with the identity reference. Create ONE vertical 4:5 studio image containing a precise 6-column by 8-row grid of 48 equally sized portrait panels. Every cell shows the same clearly adult man, age 25 or older, with the same recognizable face, natural medium-length dark hair and simple white shirt; only his facial expression and, in selected cells, one small natural hand gesture may change. Lock every panel to the same head-and-shoulders crop, eye-level perspective, lighting, wardrobe and white seamless background. Use thin, even white gutters, no outer border, no labels, numbering or text. Arrange the 48 distinct expressions from left to right, top to bottom in this order: Row 1—neutral, subtle smile, full smile, laugh, smirk, raised eyebrow. Row 2—wink, surprise, shock, wide-eyed look, open-mouth expression, dramatic gasp. Row 3—side-eye, squint, anger, frown, clenched jaw, puffed cheeks. Row 4—tongue out, exaggerated grin, playful mock scream, intense stare, skeptical look, confused look. Row 5—doubtful smirk, playful cross-eye, big laugh, mock cry, hands on cheeks, fingers forming binoculars around eyes. Row 6—partial face cover, gentle mouth-corner stretch, chin on fist, overjoyed grin, serious stare, calm look. Row 7—narrowed eyes, mock frustration, dramatic sigh, exaggerated shock, goofy face, proud smile. Row 8—sarcastic grin, puzzled head tilt, confident smirk, blank expression, relaxed finishing pose, soft closed-eye smile. Keep all expressions clearly different but anatomically believable; avoid warped features, misaligned eyes or duplicated/missing fingers. Use soft frontal studio portrait lighting with balanced fill and minimal shadow, crisp focus on each face, consistent scale and clean editorial rendering. No other people, props, text, logos or watermark.
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
相关作品
- 梦回江户浮世绘古典人物像
A reference-led Edo-period ukiyo-e portrait transformation that preserves the supplied person’s facial identity while restyling hair, clothing and accessories in traditional Japanese fashion. The current ref-10a-v1 is the generic person preview for this workflow, not a claim about any external named
- 盛世长安万国来朝图
A text-driven historical reconstruction of the source scene: an aerial view of Kaiyuan-era Chang’an, Emperor Xuanzong and Yang Guifei looking out from Hanyuan Hall, and a distant tribute procession. The configured generic portrait is used only as a face-identity anchor for Yang Guifei in this genera
- 威震天高定西装时尚大片
A text-driven fashion-cover portrayal of Megatron, retaining the source's silver-gray mecha, haute-couture suit and cyberpunk neon setting; it does not claim an exact adaptation-specific design. / 依据文字创作的威震天时尚封面，保留银灰机甲、高定西装与赛博朋克霓虹场景；不声称复现某一改编版本的精确造型。
- 黑木崖红衣飞针傲立悬崖
An original cinematic wuxia interpretation of the named fictional character, preserving the source's flying embroidery needles, red clothing, long hair, Heimuya cliff and blood-red sunset. The configured generic portrait is used only as the required face identity anchor, not as a canonical character
- 李佳琦口红矩阵直播间背景
A fictional, unoccupied livestream-commerce background with a lipstick matrix display wall, warm ambient lighting and the source's exact English visible copy. It does not claim to reproduce Li Jiaqi's actual studio. / 虚构的无人直播带货背景，包含口红矩阵展示墙、暖光氛围灯与来源要求的准确中文可见文案；不声称复刻李佳琦的真实直播间。
- 复古报纸主角头版设计
A realistic vintage newspaper cover placing the configured adult-woman portrait as the unchanged, recognizable central article photo, with fictional editorial text and print details. / 逼真的复古报纸头版，将配置的成年女性肖像作为保持原样且清晰可辨的中央主照片，并配以虚构编辑文字和印刷细节。