OpenZhenZhen AI 提示词画廊 · gpt-image-2.5 · image
成年女性俏皮挡镜头人像
Playful Adult Woman Blocking the Camera Portrait
基于输入人像进行身份一致的编辑：一位明确成年女性以俏皮不悦表情抬手靠近镜头、仿佛挡住拍摄，背景替换为干净纯粉色影棚底色。
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。 编辑输入人像中的同一位明确年满25岁的成年女性。保留她的面部身份、五官、肤色、发型、服装和配饰；不要换脸或加入其他人物。只改变表情、伸手姿势和背景。让她微微皱眉并轻轻嘟嘴，呈现俏皮假装不悦的神情，像是在打趣地说“别拍我”；不要添加文字或对话气泡。让她略微向镜头前倾，并将一只自然的手伸近镜头，仿佛轻轻挡住画外的手机。利用近大远小的透视让前景手显得大而醒目，约占画面三分之一，手掌可见、五指自然；手后方的面部仍须清晰可辨并准确对焦。将背景替换为干净纯色的粉色无缝影棚背景。保留原图的整体摄影质感和其他未指定修改的细节。采用近距离广角的视觉透视以强调纵深，但不保证具体实体镜头参数。画面不出现第二个人或可见手机；避免多指、手指粘连、肢体畸形、严重模糊、文字、水印、边框、服装或发型变化以及视觉风格改变。
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. Edit the input portrait of the same clearly adult woman, age 25 or older. Preserve her facial identity, features, skin tone, hairstyle, outfit and accessories; do not face-swap or introduce another person. Change only the expression, reaching pose and background. Give her a playful mock-annoyed expression with lightly furrowed brows and a small pout, as if teasingly saying “stop filming me”; do not add words or a speech bubble. Lean her slightly toward the camera and bring one natural hand close to the lens as if gently blocking the unseen phone. Let the foreshortened foreground hand feel large and prominent, roughly one-third of the frame, with a visible palm and five naturally formed fingers; keep her face clearly recognizable and sharply focused behind it. Replace the background with a clean, solid pink seamless studio backdrop. Retain the original image's overall photographic character and all unchanged source details. Favor a close wide-angle perspective to emphasize depth, without guaranteeing exact physical lens settings. Show no second person or visible phone; avoid extra or fused fingers, distorted anatomy, heavy blur, text, watermark, frame, outfit/hair changes or a different visual style.
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
- 高级商务证件照头像海报设计
使用当前配置的人像参考制作正式商务头像海报，保留人物身份，并以可替换的姓名、职位和机构资料呈现英文信息栏。 Create a formal business headshot poster from the configured portrait reference, preserving the person’s identity and displaying replaceable name, position and institution details in an English information bar.
- 人物与涂鸦结合的肖像照
A low-angle editorial portrait using the configured reference subject, styled with a pastel bucket hat, gray sweatshirt and round sunglasses beneath a doodle-filled blue sky. 使用当前配置参考中的人物创作低角度编辑风肖像，搭配马卡龙色渔夫帽、灰色卫衣和圆形墨镜，置于涂鸦点缀的蓝天下。
- 童话立体书奇幻主角照
A reference-based protagonist explores a cinematic handcrafted popup-book fairytale, rendered as a layered paper diorama viewed from above. 使用当前人物参考作为主角，在电影感手工弹出式童话书世界中探索；以俯视角呈现层叠纸艺立体模型。
- 高分辨率 Q 版克隆贴纸日记照
A centered real-person social diary portrait with a balanced ring of matching chibi stickers, light doodles and short handwritten English phrases. 使用真实人物居中的社交日记风人像，周围环绕外观匹配的Q版贴纸、轻盈涂鸦和英文手写短语。
- 4K 超高清时尚肖像
A luxury couture-inspired editorial mirror portrait using the configured generic identity reference, with cinematic studio lighting and premium fabric detail.
- AI智能换装试穿对比海报
A four-section 16:9 fashion try-on and pose showcase, using the configured generic identity reference, a coordinated outfit flatlay, a matching try-on result, and six poses.