Thư viện prompt AI OpenZhenZhen · gpt-image-2.5 · image

Chân dung hành lang phòng trưng bày xoáy quang học

Optical Vortex Gallery Corridor Portrait

Chân dung hành lang phòng trưng bày xoáy quang học — khám phá tác phẩm được tạo bằng gpt-image-2.5 trên OpenZhenZhen, kèm prompt gốc và ví dụ tạo nội dung để tham khảo.

Chân dung hành lang phòng trưng bày xoáy quang học — AI image creation
Chân dung hành lang phòng trưng bày xoáy quang học

Prompt

Prompt tiếng Trung

创作一张自然写实的竖幅画廊走廊人像，主体为身份参考 ref-10a-v1 中明确成年的女性，保持面部身份一致。她留乌黑及腰直发与中分，佩戴简洁银色耳环，身穿不透的橄榄绿罗纹短袖圆领上衣和舒适的深色高腰牛仔短裤，下摆整齐；衣着得体，不强调身体曲线。她放松地靠向左侧墙面，头部轻靠哑光黑白光学旋涡壁画；身体相对镜头转约10度，一只手臂自然垂放，另一只手臂保持舒适放松。她神情平静，目光柔和地望向镜头旁。现代简洁的短走廊左墙为黑白旋涡图案，右墙挂有原创的单色漫画分格装饰；只用抽象、不可辨读的符号，不仿制任何特定漫画、角色或品牌。浅灰抛光地面上铺一块哑光灰色区域以减弱反光。主体位于画面左侧三分之一，右侧保留漫画装饰可见，背景轻微虚化但结构清楚，走廊垂直线保持端正。使用柔和宽阔的顶面主光、较弱的白色反射补光与相机右后方窄条轮廓光；阴影柔和，头发高光细腻，皮肤保持自然，避免塑料质感。全画幅无反相机配50毫米定焦，f/3.2、1/250秒、ISO 400、约4600K白平衡，机位在胸口高度并保持低畸变。采用4:5竖幅大腿中部人像构图，头顶留少量空间。保持冷中性色调、真实肤色、自然毛孔、布料织纹与发丝细节，适度降噪和锐化。避免可辨文字、虚构标牌、水印、品牌图案、过度磨皮、硬阴影、广角畸变及错误肢体或手指。

Prompt tiếng Anh

Create a natural, photorealistic vertical gallery-hall portrait of the clearly adult woman in the fixed identity reference ref-10a-v1, preserving her facial identity. She has waist-length straight jet-black center-parted hair and simple silver hoop earrings. Dress her in an opaque olive-green ribbed short-sleeve crew-neck top and comfortable high-waisted dark denim shorts with a neat finished hem: opaque, tasteful clothing without body-emphasizing styling. She leans casually toward the left wall, her head lightly resting against a matte black-and-white optical-swirl mural; turn her body about 10 degrees to camera, let one arm rest naturally at her side and keep the other comfortable and relaxed. Her expression is calm, with a soft gaze just past the camera. The modern uncluttered short corridor has a monochrome swirl mural on the left wall and framed original monochrome comic-panel decor on the right; use abstract, unreadable marks only, with no imitation of a particular comic, character or brand. A matte gray floor area reduces reflections on the light-gray polished tile. Place the subject in the left third, keep the comic decor visible on the right, and softly defocus but retain readable structure in the background; keep corridor verticals straight. Light with a broad soft overhead key, weaker white bounce fill, and a narrow rear strip light camera-right; keep shadows soft, hair highlights delicate and skin natural rather than plastic. Use a full-frame mirrorless camera with a 50 mm prime, f/3.2, 1/250 s, ISO 400 and about 4600 K white balance at chest height with low distortion. Frame a 4:5 vertical mid-thigh portrait with a little space above the head. Keep a neutral-cool grade, natural skin tone and pores, fabric weave and hair detail, with restrained noise reduction and sharpening. Avoid legible text, invented signage, watermark, brand marks, excessive smoothing, hard shadows, wide-angle distortion and malformed anatomy or fingers.

Xem mô hình API

Xem thêm prompt hình ảnh và video · Tạo hình ảnh · Tạo video · Tạo trên canvas AI