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

Sáng Tanabata: thiếu nữ yukata cầu nguyện tại đền

Tanabata Morning: Shrine Maiden in Yukata Praying

Sáng Tanabata: thiếu nữ yukata cầu nguyện tại đền — 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.

Sáng Tanabata: thiếu nữ yukata cầu nguyện tại đền — AI image creation
Sáng Tanabata: thiếu nữ yukata cầu nguyện tại đền

Prompt

Prompt tiếng Trung

生成一张超写实的七夕清晨神社人像:一位二十多岁的成年日本女性站在传统神社中。她拥有柔和椭圆脸、自然通透的肤质、清淡日系妆容,深棕色头发松散地梳成低发髻,几缕细碎发丝被晨光照亮,耳后别着小型紫色发饰。她穿一件得体的蓝色棉质浴衣,腰带位置整齐,带有雅致季节纹样。让她的脸部略微抬起,目光注视右上方的一条短签,右手指尖轻轻触碰或握住短签,手与纸张的接触必须自然。短签上用细腻清晰的手写体准确写出愿望 願いが届きますように。采用竖幅人像构图,保持人物与短签之间的距离,焦点放在面部和指尖,背景的神社灯笼与远处参道采用浅景深柔和虚化。使用明亮的高调晨间逆光,保留自然毛孔、细碎发丝、棉质浴衣纹理和半透明纸张质感,以透明白、浅绿和蓝色为主,加入少量胶片颗粒与自然镜头光晕。不要不自然的视线、手指畸形、手腕破损、浴衣结构崩坏、腰带错位、过度美肌、塑料感皮肤、乱码文字、标志、水印、其他人物、过度暴露或与背景矛盾的阴影。

Prompt tiếng Anh

Create a photorealistic Tanabata morning portrait of one adult Japanese woman in her twenties at a traditional shrine. Give her a soft oval face, natural translucent skin, light Japanese makeup, dark-brown hair loosely tied in a low bun, a few fine strands glowing in morning light, and a small purple hair ornament tucked behind one ear. She wears a refined blue cotton yukata with a neatly placed sash and tasteful seasonal pattern. Tilt her face slightly upward and have her eyes follow a short tanzaku wish strip in the upper-right while her right fingertips gently touch or hold it; keep the hand-to-paper contact anatomically natural. Write the exact wish 願いが届きますように on the strip in delicate legible handwriting. Use a vertical portrait with clear distance between the woman and the tanzaku, focus on her face and fingertips, and softly blur shrine lanterns and the distant path. Use bright high-key morning backlight, natural pores, wispy hair, cotton texture, translucent paper, pale green and white highlights, blue yukata tones, subtle film grain, and a gentle lens flare. No unnatural gaze, malformed fingers, broken wrists, collapsed yukata, misplaced sash, excessive smoothing, plastic skin, garbled text, logos, watermark, extra people, excessive exposure, or contradictory shadows.

Xem mô hình API

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