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

床上侧望成年女性与象征阴影

Adult Woman Lying on Bed with Symbolic Shadows

4:3横幅仰卧脸部特写：明确成年女性侧望镜头外，脸部出现唯一受控的圆柱形圆顶端象征性阴影，脸部以下出框。

床上侧望成年女性与象征阴影 — AI image creation
床上侧望成年女性与象征阴影

提示词 / Prompt

中文提示词

使用上传的人物身份参考图保留明确成年主要女性的面部身份。创作一张电影感写实4:3横幅脸部特写：她仰卧在床上，脸部以下全部出画。视线转向侧面，不直接看镜头。脸部只投射一条粗壮的象征性阴影：阴影应呈受控的圆柱形，末端为圆顶形，柔和融入光线，不作为实体物体出现。阴影长度适中、比例自然且清晰可辨，不得过长或变形。使用克制的卧室光线、真实皮肤纹理和柔和明暗过渡，不加入其他象征形状、文字或水印。画面保持非裸体且不包含性行为，避免图形化或露骨解读。

English prompt

Use the uploaded identity reference image to preserve the facial identity of the clearly adult main woman. Create a cinematic photorealistic 4:3 horizontal face close-up of her lying on a bed, with everything below the face outside the frame. Turn her gaze to the side rather than directly at the camera. Cast exactly one thick symbolic shadow across the face: it should read as a controlled cylindrical form with a rounded dome-shaped tip, softly integrated into the lighting and not physically present as an object. Keep the shadow concise, proportionate, and clearly legible without extending too far or becoming distorted. Use restrained bedroom light, realistic skin texture, gentle tonal transitions, and no other symbolic shapes, text, or watermark. The portrait remains non-nude and contains no sexual activity; avoid graphic or explicit interpretation.

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

  • 1girl

    gpt image2.5生成

  • 【超必杀】圣光白米大肥鱼

    整体基调：东方史诗神话灾难大片质感，热血动漫爆发感融合好莱坞写实CG，UE5电影渲染，HDR光追，真实物理，强烈金色侧逆光，体积沙尘，电影景深，动态运动模糊，节奏干脆迅猛。 图1锁定角色：蓝渐变长卷发，头顶呆毛，鲸鲨鱼耳，鲸鲨长尾，女仆裙装，白色围裙，围裙印有小鲸鱼图案，Q版比例。 图2锁定巨型黑黄条纹甲壳虫王，巨口獠牙、尖刺前爪、虫群头领气质。 图3只用于冲击帧视觉语言【严格遵循Impact Frame规则】：冲击帧不是连续动画，不是撕裂米粒浪潮喷涌过程，也不是爆炸过程，而是**米粒旋风接触虫王躯干的命中顶点瞬间，强行打断正常运动、插入极短静态定格画面的视觉卡点**。冲击帧仅0.2秒，帧内无

  • 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。