OpenZhenZhen AI 提示词画廊 · gpt-image-2.5 · image
后台操纵自我木偶的舞台肖像
Stage Portrait of a Backstage-Operated Self-Puppet
在剧院后台，一位成年表演者用提线控制杆操纵一个代表自己的小型木偶，形成简洁、略带超现实感的剧场编辑摄影。
提示词 / Prompt
中文提示词
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. 创作一张具有剧场编辑感的写实照片：一位明确成年表演者（25岁以上）站在剧院后台化妆间，双手握着木偶十字控制杆，正在操纵一个代表自己的小型提线木偶。表演者的面部身份由配置参考图ref-10a-v1引导并保持可辨认一致，不承诺完全复制；木偶是同一成年人物的风格化微缩复制品，发型、主要面部轮廓和服装色调与表演者呼应，但材质清楚呈现为木质或布面关节玩偶，不能像第二个真人。细线从控制杆连接到木偶的肩、腕和膝部，走向清楚且不缠绕。表演者以专注而平静的神情低头看向木偶，动作自然、手指结构正确。背景有带灯泡的化妆镜、挂衣架与柔和虚化的舞台幕布，暗示剧院后台而不显杂乱。使用暖色镜前灯与少量冷色舞台侧光形成层次，浅景深突出表演者、控制杆和木偶，保留真实皮肤、木材、布料和提线细节。构图表达表演者与自我复制木偶之间微妙的戏剧关系，克制、诗意且轻微超现实。不要出现额外人物、文字、剧院标志、水印、断裂提线或多余肢体。
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 realistic theatrical editorial photograph of a clearly adult performer, age 25+, in a theater dressing room backstage, using a hand-held marionette control cross to operate a small puppet that represents themself. Guide the performer's facial identity with configured reference ref-10a-v1 and keep it recognizably consistent without promising an exact copy. The puppet is a stylized miniature of the same adult, echoing hairstyle, broad facial silhouette and clothing colors, but unmistakably made as a jointed wood or fabric doll rather than a second living person. Show fine strings clearly running from the control cross to the puppet's shoulders, wrists and knees without tangling. The performer looks down toward the puppet with a calm, focused expression and natural hand pose. In the softly blurred background, include a bulb-lit dressing mirror, a garment rack and a hint of stage curtain to establish backstage without clutter. Layer warm mirror bulbs with a touch of cool stage-side light; use shallow depth of field to emphasize performer, control cross and puppet while retaining believable skin, wood, fabric and string detail. The composition should suggest a subtle dramatic relationship between a performer and their own miniature double, poetic and slightly surreal but restrained. No extra people, text, theater logos, watermark, broken strings or duplicated limbs.
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
相关作品
- 特斯拉电动车核心部件示意全景
横向概念示意海报：以未指定车型的特斯拉电动车为中心，周围安排若干模块放大细节。电池包、电驱电机、逆变器/电力电子、车载充电器、热管理回路、悬架与制动、充电接口均为整理者选定的示意模块，不是来源列明的清单，也不代表特定车型布局或工程规格。 / A landscape conceptual overview centered on a Tesla EV of unspecified model, surrounded by selected module detail callouts. Battery pack, drive motor, inverter/power electronics,
- 日系负片里的记忆碎片
A 9:16 candid Japanese negative-film style portrait. The adult person, unposed walk and quiet neighborhood lane are replaceable curator-selected defaults, not subject or scene details supplied by the source. The currently configured ref-10a-v1 is used as the generic person identity reference and is
- 1girl
gpt image2.5生成
- 法式风情地标美食海报
A premium, clean and elegant poster concept built from the source’s broad request. Eiffel Tower, Arc de Triomphe, ratatouille and Provençal bouillabaisse are curator-selected illustrative examples, not details stated by the source; they can be replaced in a future variant. The source example image i
- 梦回江户浮世绘古典人物像
A reference-led Edo-period ukiyo-e portrait transformation that preserves the supplied person’s facial identity while restyling hair, clothing and accessories in traditional Japanese fashion. The current ref-10a-v1 is the generic person preview for this workflow, not a claim about any external named
- 盛世长安万国来朝图
A text-driven historical reconstruction of the source scene: an aerial view of Kaiyuan-era Chang’an, Emperor Xuanzong and Yang Guifei looking out from Hanyuan Hall, and a distant tribute procession. The configured generic portrait is used only as a face-identity anchor for Yang Guifei in this genera