OpenZhenZhen AI 프롬프트 갤러리 · gpt-image-2.5 · image
불꽃 케밥과 중동 길거리 음식 삼면화
Blazing Shawarma and Middle Eastern Street Food Triptych
‘불꽃 케밥과 중동 길거리 음식 삼면화’은(는) gpt-image-2.5로 만든 작품입니다. OpenZhenZhen에서 원본 프롬프트와 생성 예시를 살펴보고 새로운 창작에 활용해 보세요.
프롬프트
중국어 프롬프트
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。为成年食品制作者实际绑定身份参考 ref-10a-v1；画面仅显示戴手套的双手，不露面。创作精致的3:2横幅美食摄影三联画，分成三个清晰区隔且视觉协调的画面。第一格：近景呈现烤卷饼与三明治，可见炭烤痕迹，内有烤肉、新鲜蔬菜、香草和奶油酱，配以轻柔热气和少量酱汁滴落。第二格：一只热卷饼仅由成年食品制作者戴手套的双手拿着，旁边是受控的明火。第三格：中东街头小吃俯拍，木碗中盛有鹰嘴豆泥、甜菜蘸酱、绿色酱汁、腌菜和法拉费卷。第一格采用近距离美食特写，炭烤痕、酥脆质地、新鲜香草、轻柔热气和适量酱汁清楚可见。第二格使用暖火光与深色哑光台面；明火受控并留在背景，食品处理安全自然。第三格为质朴俯拍平铺，木碗、蘸酱、腌菜与法拉费卷摆放均衡。整体采用暗调环境、温暖火光高光、浓郁诱人的食物质感与选择性浅景深，同时确保每道菜清晰可辨。避免过量烟雾、食物被遮挡、呈生肉观感、道具杂乱、其他人物、品牌、可读文字、水印及无依据的8K或完美画质保证。
영어 프롬프트
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. Attach the required identity_reference file ref-10a-v1 for the adult preparer; show only gloved hands, no face. Create a polished 3:2 landscape food-photography triptych with three cleanly separated, visually coherent panels. Panel 1: close-up grilled wraps and sandwiches with char marks, grilled meat, fresh vegetables, herbs, creamy sauce, gentle steam and a few sauce drips. Panel 2: one hot wrap held only by an adult preparer's gloved hands beside a controlled open flame. Panel 3: overhead Middle Eastern street-food spread with hummus, beet dip, green sauces, pickled vegetables and falafel wraps in wooden bowls. Panel 1 is a close macro food shot with clear grill marks, crisp textures, glossy but controlled sauce, fresh herbs and gentle steam. Panel 2 uses warm firelight and a dark matte surface; keep the open flame contained in the background, with no unsafe handling. Panel 3 is a rustic overhead flat lay with balanced spacing among the wooden bowls, dips, pickles and falafel wraps. Use moody dark surroundings, warm firelit highlights, rich appetizing textures and selective shallow depth of field while keeping each dish legible. Avoid excessive smoke, obscured food, raw-looking meat, chaotic props, extra people, branding, readable text, watermark and unsupported 8K or perfect-quality claims.
더 많은 이미지·동영상 프롬프트 보기 · 이미지 생성 · 동영상 생성 · AI 캔버스에서 만들기