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

2D卡通贴纸实景混合构图

2D Cartoon Stickers in Real-World Scenes

将上传的人物身份参考转化为带白色贴纸边框的 2D 卡通角色,让其以指定动作穿过真实拍摄的指定地点,形成插画角色与实景环境的混合媒体构图。

2D卡通贴纸实景混合构图 — AI image creation
2D卡通贴纸实景混合构图

提示词 / Prompt

中文提示词

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。 将人物渲染为保留参考图面部身份特征的 2D 卡通贴纸;不要生成写实摄影人像。 a cartoon character based on the reference person walking 穿过 a real city street,大胆清晰的轮廓,扁平鲜艳的色彩,简化的卡通比例,真实的摄影环境,真实的天气和自然运动,插画角色与真实世界背景之间强烈的视觉对比,无缝的混合媒体构图,电影感的街头摄影,角色周围有白色贴纸边框。 --ar 3:4

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. Render the person as a stylized 2D cartoon sticker that preserves the reference facial identity cues; do not turn the result into a photorealistic camera portrait. a cartoon character based on the reference person walking through a real city street, bold clean outlines, flat vibrant colors, simplified cartoon proportions, authentic photographic environment, realistic weather and natural motion, strong visual contrast between the illustrated character and the real-world background, seamless mixed-media composition, cinematic street photography, white sticker border around the character. --ar 3:4

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。