OpenZhenZhen AI 提示词画廊 · gpt-image-2.5 · image
九宫格中的同一成年女性情绪与造型拼贴
Collage of the Same Adult Woman's Emotions and Styles in a Nine-Grid
一张3×3编辑拼贴，八格展示同一成年女性身份的不同表情、发型和穿搭，从喜悦、惊讶、沉思到俏皮与自信；右下角留白。每格采用协调的柔和纯色影棚背景，呈现简洁的时尚肖像变化，同时保持面部身份高度一致。 An editorial 3×3 collage uses eight cells to show one adult woman's consistent identity across varied expressions, hairstyles, and outfits—from joyful and surprised to thoughtful, playful, and confident
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。 创作一张整洁的3×3时尚人像拼贴：八个单独画格中始终是同一位明确成年的女性，严格保持参考图所示的面部身份与五官结构一致，只改变表情、发型、服装和背景色。按清晰网格排列：左上灿烂微笑、双手轻轻框住脸；上中惊讶表情、长波浪发与米色T恤；右上略带忧思、手托下巴、灰色针织衫与凌乱盘发；中左温柔直视、半扎发与奶油色上衣；正中自信凝视、后梳发型与黑色机车夹克；中右俏皮皱鼻、短卷波波头与蓝白条纹衬衫；左下自然眨眼、手指轻点脸颊、双丸子头与纯色深灰T恤；下中惊讶张口、双手扶头、蓬松散发与简洁白衬衫。所有服装无文字或图案。八格背景分别采用浅蓝、桃色、薰衣草灰、暖棕、深青、薄荷绿、浅粉和淡黄，色彩柔和协调。每格为头肩或半身近景，人物大小、视角、柔和影棚光与清晰度一致；网格线细而整齐。右下格留作干净留白，不生成第九张人物照。自然肤质、真实但不过度锐化，不指定相机、镜头或分辨率。画面无文字、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 a clean 3×3 fashion-portrait collage. The same clearly adult woman appears in eight separate cells; preserve the exact facial identity and feature structure from the reference in every cell, changing only expression, hairstyle, outfit, and backdrop color. Arrange the expressions clearly: top-left, bright smile with hands gently framing the face; top-middle, surprised expression, long loose waves and beige T-shirt; top-right, thoughtful gaze with hand at chin, gray knit sweater and relaxed updo; middle-left, tender direct gaze, half-up hair and cream top; center, confident look, slicked-back style and black moto jacket; middle-right, playful scrunched nose, short curly bob and blue-white striped shirt; bottom-left, natural wink with a finger lightly touching the cheek, double buns and plain dark-gray tee; bottom-middle, surprised open mouth with hands at the head, voluminous loose hair and simple white blouse. All clothing is free of text and graphics. Use coordinated soft studio backdrops in light blue, peach, lavender-gray, warm tan, deep teal, mint, light pink, and pale yellow. Keep each portrait head-and-shoulders or medium close-up, with consistent subject scale, viewpoint, soft studio lighting, and clarity; use neat thin grid dividers. Leave the bottom-right cell clean and empty as breathing room rather than adding a ninth portrait. Natural skin texture, realistic but not over-sharpened; do not specify camera, lens, or resolution. No 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
- 暗黑大肥鱼
整体基调：东方史诗神话灾难大片质感，暗黑恶魔动漫爆发感融合好莱坞写实CG，UE5电影渲染，HDR光追，真实物理，强烈黑金色侧逆光，深红体积沙尘与恶魔烟尘，电影景深，动态运动模糊，节奏干脆迅猛，黑红金主色，地狱化战场氛围。 图1锁定角色：蓝渐变长卷发，头顶呆毛，鲸鲨鱼耳，鲸鲨长尾，女仆裙装，白色围裙，围裙印有小鲸鱼图案，Q版比例。角色造型保持不变，但整体气质改为暗黑恶魔审判者感，表情冷冽、嘲弄、残忍，动作像恶魔刽子手执行处刑。 图2锁定巨型黑黄条纹甲壳虫王，巨口獠牙、尖刺前爪、虫群头领气质。 图3只用于冲击帧视觉语言【严格遵循Impact Frame规则】：冲击帧不是连续动画，不是撕裂米粒
- 特斯拉电动车核心部件示意全景
横向概念示意海报：以未指定车型的特斯拉电动车为中心，周围安排若干模块放大细节。电池包、电驱电机、逆变器/电力电子、车载充电器、热管理回路、悬架与制动、充电接口均为整理者选定的示意模块，不是来源列明的清单，也不代表特定车型布局或工程规格。 / A landscape conceptual overview centered on a Tesla EV of unspecified model, surrounded by selected module detail callouts. Battery pack, drive motor, inverter/power electronics,
- 日系负片里的记忆碎片
A 9:16 candid Japanese negative-film style portrait. The adult person, unposed walk and quiet neighborhood lane are replaceable curator-selected defaults, not subject or scene details supplied by the source. The currently configured ref-10a-v1 is used as the generic person identity reference and is
- 1girl
gpt image2.5生成
- 法式风情地标美食海报
A premium, clean and elegant poster concept built from the source’s broad request. Eiffel Tower, Arc de Triomphe, ratatouille and Provençal bouillabaisse are curator-selected illustrative examples, not details stated by the source; they can be replaced in a future variant. The source example image i
- 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