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

成年女性四宫格搞怪手机自拍拼贴

Adult Woman Four-Panel Funny Phone Selfie Collage

同一位成年女性以四格手机自拍呈现吐舌、闭眼微笑、眨眼和俏皮飞吻等表情，采用随性低保真社交媒体风格。

成年女性四宫格搞怪手机自拍拼贴 — AI image creation
成年女性四宫格搞怪手机自拍拼贴

提示词 / Prompt

中文提示词

创作一张随性的2×2网格拼贴，由同一位明确成年女性拍摄四张前置手机自拍；主体为 identity_reference ref-10a-v1，并在每一格保持面部身份一致。四个等大画幅置于竖向、接近4:5的构图画布中，将比例作为构图方向而非像素保证。她穿覆盖得体、穿着舒适的简洁白色背心，头发自然放松，整体健康、随意、不性感化。四格分别呈现不同搞怪表情：斗鸡眼并顽皮吐舌；闭眼温柔微笑；开心眨眼并露出笑容；以及凑近手机镜头做俏皮飞吻，嘴唇靠近但不接触设备。采用手持、手臂长度的自拍视角，带轻微广角感。使用柔和随意的室内环境光，呈现真实未经修饰的社交媒体自拍质感，可带细微胶片颗粒、轻微噪点、偶尔不完美的对焦和略不均匀的曝光。避免影棚或光鲜杂志质感、夸张解剖结构、过度修图，不增加人物、文字、标志或水印。

English prompt

Create a casual 2x2 collage of four spontaneous front-facing smartphone selfies of the same clearly adult woman in identity_reference ref-10a-v1, preserving her facial identity consistently in every frame. Use four equal panels on a vertical 4:5-oriented canvas as framing guidance. She wears a simple white tank top with comfortable secure coverage and relaxed hair; keep the styling natural, wholesome and non-sexualized. Give each frame a distinct goofy expression: crossing her eyes with a playful tongue-out face; a soft smile with eyes closed; a cheerful wink and grin; and leaning toward the phone for a playful air-kiss toward the lens, lips close to but not touching the device. Keep the handheld arm's-length selfie perspective with mild wide-angle feel. Use soft casual indoor ambient light and an authentic unpolished social-media look, with subtle film grain, slight noise, occasional imperfect focus and gently uneven exposure. Avoid studio or glossy editorial polish, exaggerated anatomy, heavy retouching, extra people, text, logos or watermark.

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

  • 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