OpenZhenZhen AI 프롬프트 갤러리 · gpt-image-2.5 · image

고목 가지 위 당풍 악단 환상도

Fantasy of a Tang-Style Band on Ancient Branches

‘고목 가지 위 당풍 악단 환상도’은(는) gpt-image-2.5로 만든 작품입니다. OpenZhenZhen에서 원본 프롬프트와 생성 예시를 살펴보고 새로운 창작에 활용해 보세요.

고목 가지 위 당풍 악단 환상도 — AI image creation
고목 가지 위 당풍 악단 환상도

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。 创作一幅超现实、极简写实风格的东方音乐场景:五位明确成年、穿着受唐代服饰启发但不声称历史复原的乐手,分散坐立于一根宽阔稳固的古树枝干上,演奏琵琶、二胡、笛子、阮和马头琴。前景领奏者面部清晰并遵循上传参考图;其余四位乐手以较小比例、侧身或背向呈现,所有可见人物的身份特征均以同一参考图为依据,服饰配色和姿态各异。数只小鸟在枝干与乐器间自然停栖,营造轻松灵动的气氛。背景为柔和驼棕色,如舞台画布般平整简洁;采用均匀柔和光线、克制留白、细腻乐器纹理和柔和阴影。整体兼具古典乐队意象与梦幻编辑插画气质,不标注真实历史事件或朝代考据。不得出现错误的乐器结构、危险坠落动作、现代设备、商标、水印或杂乱文字。

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. Create a surreal, minimalist-realistic East Asian musical scene. Five clearly adult musicians, wearing broadly Tang-inspired costumes without claiming historical reconstruction, are scattered in seated and standing poses along one broad, sturdy ancient-looking tree branch, playing pipa, erhu, dizi flute, ruan, and horse-head fiddle. The foreground lead musician has a clearly visible face consistent with the uploaded reference; the other four performers are smaller and shown in profile or from behind. All visible people use the same reference identity, while their costume colors and poses vary. A few small birds perch naturally among the branch and instruments, adding a light, lively mood. Set the scene against a soft camel-brown color, like a simple stage-canvas backdrop; use even gentle light, restrained negative space, delicate instrument textures, and soft shadows. Blend a classical ensemble image with a dreamy editorial-illustration sensibility, without asserting a real historical event or scholarly reconstruction. Avoid incorrect instrument construction, unsafe falling action, modern devices, trademarks, watermarks, or cluttered text.

API 모델 보기

더 많은 이미지·동영상 프롬프트 보기 · 이미지 생성 · 동영상 생성 · AI 캔버스에서 만들기