OpenZhenZhen AI 提示词画廊 · gpt-image-2.5 · image

角色鼻部微距写实细节特写

Macro Realistic Close-Up of Character Nose Details

将用户上传的成年角色参考图裁切并放大至鼻部微距，呈现可信细腻的皮肤与鼻部结构细节，同时保留参考主体的可见身份特征、肤色与原有造型，不添加磨皮或虚构纹理. A reusable image recipe made with gpt-image-2.5; explore the prompt and related works in the gallery.

角色鼻部微距写实细节特写 — AI image creation
角色鼻部微距写实细节特写

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。 将同一位明确25岁或以上的成年角色制作成照片级鼻部微距编辑，仅使用ref-10a-v1保持可见面部身份，不推断个人经历。从鼻梁下段至上唇进行极近距离裁切，并包含两个鼻孔。保留参考图真实的鼻形、肤色与可辨识面部特征；呈现自然细致的毛孔与微妙皮肤纹理，忠实贴合参考图，以真实而克制的方式还原，避免磨皮美化或人为添加瑕疵。采用柔和中性的漫射光与轻微轮廓阴影；清晰对焦于鼻梁、鼻尖和鼻孔边缘，并向周围逐渐浅化。人体比例保持自然，鼻孔边缘清晰，景深浅而可控。结果应像从所提供参考图忠实放大的高品质微距照片，而不是换成另一人或重新设计五官。不要未成年人、医疗操作、伤害、侵入性器械、夸张毛孔、结构变形、文字、Logo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 photorealistic macro edit of the same clearly adult character, age 25 or older, using ref-10a-v1 only to preserve visible facial identity and without inferring biography. Reframe to an extreme close crop from the lower bridge of the nose to the upper lip, including both nostrils. Preserve the reference's actual nose shape, skin tone and recognizable facial characteristics; render natural fine pores and subtle skin texture, faithfully matching the reference with realistic, restrained texture rather than beauty retouching or artificial blemishes. Use soft neutral diffused light with gentle contour shadows and set crisp focus on the nose bridge, tip and nostril edges with a gradual shallow falloff. Keep proportions anatomically natural, nostril edges clear and depth of field shallow but controlled. The result should feel like a high-quality macro photograph faithfully derived from the supplied reference, not a different person or a redesigned feature. No minors, medical procedure, injury, invasive instrument, exaggerated pores, distortion, text, logo or watermark.

查看 API 模型

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

  • 90年代冷色调仙侠风翡翠绿汉服人像

    Ethereal 9:16 full-body portrait of a clearly adult Chinese woman in jade-green xianxia-inspired hanfu amid layered gauze curtains, silver ornaments, and cold teal moonlight with nostalgic 1990s fantasy-drama diffusion. A reusable image recipe made with gpt-image-2.5; explore the prompt and related

  • 超精细3D漫画球星收藏级海报

    Reusable 4:5 sports-memorabilia poster template for a named football player, combining a stylized likeness, current kit, chronological miniature career display, trophies, milestone props, and engraved nickname plaque. A reusable image recipe made with gpt-image-2.5; explore the prompt and related wo

  • 复古赛车海报设计提示词

    Reusable 4:5 vertical retro racing poster template with a centered front-facing car hero view, integrated geometric landscape graphics, fictional brand mark, slogan, and distressed vintage print finish. A reusable image recipe made with gpt-image-2.5; explore the prompt and related works in the gall

  • Q版角色聊天表情包生成指令

    Reusable template for a consistent chibi chat-sticker character showing one clear emotion and action at a time, with a reserved Chinese-copy area and white or transparent background. A reusable image recipe made with gpt-image-2.5; explore the prompt and related works in the gallery. Topics include

  • 认识蜜蜂儿童科普百科海报

    Colorful classroom infographic poster centered on a friendly fuzzy honey bee, with modular anatomy, life-cycle, superpower, and conservation sections in a soft cream honeycomb design. A reusable image recipe made with gpt-image-2.5; explore the prompt and related works in the gallery. Topics include

  • 时尚色块拼贴人像摄影

    Premium fashion-campaign collage of five adult European models in separate rounded geometric panels, using royal blue, crimson, emerald, mustard, and white luxury color fields with clean studio flash. A reusable image recipe made with gpt-image-2.5; explore the prompt and related works in the galler