OpenZhenZhen AI 提示词画廊 · gpt-image-2.5 · image

夏日八套穿搭自由拼贴画

Summer 8-Outfit Free Collage

以固定女性肖像作为脸部身份参考，创作八套全身夏季穿搭的自由式双排拼贴；保持人物脸部、比例、尺度和机位一致，不在画面文字中写身高。 Create a freeform two-row editorial collage of eight full-body summer looks, using the configured portrait as the preview face identity and keeping the face, proportions, scale and camera distance consistent without printing a height.

夏日八套穿搭自由拼贴画 — AI image creation
夏日八套穿搭自由拼贴画

提示词 / Prompt

中文提示词

创作一张自由形式的时尚编辑拼贴画，展示“我”穿着8套不同的全身夏季造型，有机地排列在干净的奶油色影棚背景上。使用已配置的ref-10a-v1肖像作为脸部身份依据，并让八种造型中的面部保持一致。各造型的身体比例保持视觉连贯，整体看起来约为5英尺6英寸的身形，但不要在画面任何位置写出或印出身高。每个人物均完整全身入镜，保持相同尺度和相机距离，以平衡的两排构图有机排列。添加细微的手写风格箭头和简短标签，标出每套穿搭的关键单品。避免任何网格、边框或框式布局。画幅比例使用4:5（默认4:5）。

English prompt

Create a freeform fashion-editorial collage of me in 8 distinct full-body summer outfits, arranged organically on a clean cream studio backdrop. Use the configured ref-10a-v1 portrait as the face identity anchor and keep the same face across all eight looks. Keep body proportions visually consistent across the figures, reading approximately around 5'6, but do not write or print a height anywhere in the image. Keep every figure full-body, at the same scale and camera distance, arranged in two balanced rows with an organic, editorial flow. Add subtle handwritten-style arrows and concise labels that highlight key pieces in each outfit. Avoid any grid, borders or boxed layouts. Use the aspect ratio 4:5 (default 4:5).

查看 API 模型

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

  • 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

  • 威震天高定西装时尚大片

    A text-driven fashion-cover portrayal of Megatron, retaining the source's silver-gray mecha, haute-couture suit and cyberpunk neon setting; it does not claim an exact adaptation-specific design. / 依据文字创作的威震天时尚封面，保留银灰机甲、高定西装与赛博朋克霓虹场景；不声称复现某一改编版本的精确造型。