OpenZhenZhen AI 提示词画廊 · gpt-image-2.5 · image
动态东方古典花精灵成年女性写真
Dynamic Eastern Classical Flower Fairy Adult Woman Portrait
以用户上传的人物参考图绑定主要可见成年韩国女性的面部身份，生成一张3:4竹林薄雾中的动态东方古典写真，保留盘髻花饰、薄荷青纱裙、旋转舞动、飘飞长袖、暖色蝴蝶和高调空气感。
提示词 / Prompt
中文提示词
以用户上传的参考图作为主要可见成年女性的面部身份依据。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3:4竖幅、照片级真实的动态东方古典花精灵写真。主体是一位成年韩国女性，拥有精致韩系面容、白皙但保留真实纹理的肌肤和黑色古典盘髻，盘髻上装饰浅青白色花饰。她置身竹林与白雾之间，正在轻盈旋转舞动，双臂自然展开；人物回头看向镜头并露出明亮笑容，情绪轻快、自由、灵动。保持真实成年人体态、自然重心和清晰的动作结构，利用裙摆与长袖的大面积飞扬形成强烈流动线条。 她穿浅薄荷绿色古典纱裙，多层轻盈半透明纱、飘带和花朵刺绣层叠展开，大面积裙摆被风带起；服装保持得体覆盖、真实布料层次和自然运动。画面中可有几只暖色小蝴蝶飞舞，但不要让蝴蝶抢过人物。 背景是柔化竹林、白雾与晨光，整体为高调薄荷青和白色，空气感强，轻盈空灵。使用动态抓拍式东方摄影语言，捕捉旋转中的衣物轨迹、发丝和袖摆，同时保持人物面部清晰。保留照片级真实皮肤与纱料质感、柔和晨光和自然运动模糊。不要文字、标志、水印、拼图、静态僵硬姿势、畸形肢体、额外人物、过度锐化或厚重阴影。
English prompt
Use the uploaded reference image as the facial identity reference for the main visible adult Korean woman. Keep the source scene, styling, clothing, pose, composition, lighting and visual style unless they conflict with the identity reference. Create a 3:4 vertical photorealistic dynamic Oriental classical flower-fairy portrait. The subject is an adult Korean woman with refined Korean features, fair skin that retains real texture and a black classical bun decorated with light cyan-white floral ornaments. Place her between bamboo forest and white mist as she spins and dances lightly with both arms naturally extended. She looks back toward the camera with a bright smile and a light, free, agile emotion. Keep believable adult anatomy, natural balance and clear action structure, using the broad flight of her skirt and long sleeves to create strong flowing lines. Dress her in a light mint-green classical gauze dress with multiple layers of airy translucent gauze, streamers and floral embroidery. Let a large area of the skirt catch the wind while keeping appropriate coverage, realistic fabric layering and natural motion. A few small warm-toned butterflies may flutter in the frame, remaining subordinate to the woman. Use a softened bamboo forest, white mist and morning light in the background. Keep the overall tone high-key mint green and white with a strong sense of air, lightness and ethereal space. Use dynamic candid-style Oriental photography to capture the rotating fabric, hair strands and sleeve trails while keeping the face clear. Preserve photorealistic skin and gauze texture, soft morning light and natural motion blur. No text, logo, watermark, collage, stiff static pose, malformed limbs, extra people, oversharpening or heavy shadows.
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
- 超写实时尚杂志封面大片
以已配置的固定女性肖像为身份参考，创作坐在雕塑沙发上的超写实 VOGUE 高级时尚封面，保留指定服装、妆容、影棚光线与双语封面文案。 Create a hyper-realistic high-fashion VOGUE cover using the configured fixed woman portrait as identity reference, preserving the specified editorial styling, lighting and exact bilingual cover copy.
- 极简米色棚拍人物特写
在柔和米色影棚中制作九格杂志风肖像，九个镜头保持同一参考人物身份，同时呈现指定服装、不同取景与内省氛围。 Create a nine-frame editorial portrait grid in a soft beige studio, preserving the same reference identity across distinct specified shots, wardrobe and introspective mood.
- 质感拉满的高端商业美女广告
以已核验的当前固定女性肖像保持面部身份，制作可替换产品与品牌氛围的高端商业广告；默认产品为咖啡、氛围为奢华，不依赖特定品牌或产品图。 Create a premium commercial ad using the verified configured woman’s portrait for face identity, with replaceable product and brand mood; default to coffee and luxury without requiring a specific brand or product image.
- 高级极简人像海报设计
以当前固定人像作为本次原始人物照片，制作3:4竖版高级极简肖像海报；保留人物可见身份、发型、发色、服装和姿势，并用可替换的三行英文默认文案。 Use the configured portrait as this preview’s original photo for a 3:4 minimalist poster, preserving visible identity and appearance with three replaceable English copy lines.
- 超写实随性短发少女特写
以当前固定人像中的人物面部身份为参考，创作暖光、随性自拍感的超写实短发特写；短波波头是来源明确要求的造型转换。 Create a warm, casual selfie-like hyper-realistic short-bob portrait using the configured portrait for face identity; the bob is the source-requested hairstyle transformation.
- 家庭家务 4x4 灰度故事板
制作包含16个连续家务步骤的4×4灰度3D教学故事板，使用已核验的人像参考统一角色面部身份；不声称参考图中未显示的全身比例已被精确匹配。 Create a monochrome 4×4 3D instructional storyboard of sixteen household chores, using the verified portrait reference to keep the character’s face and visible identity consistent without claiming exact unseen full-body proportions