OpenZhenZhen AI 提示词画廊 · gpt-image-2.5 · image
民俗艺术水粉与记号笔风格肖像编辑
Folk Art Gouache and Marker Style Portrait Edit
将上传身份参考照片编辑为扁平民俗艺术水粉与记号笔插画,保留原人物与车内构图关系。

提示词 / Prompt
中文提示词
将上传的身份参考照片编辑为风格化的扁平民俗艺术水粉与记号笔插画,不凭空创作新场景。保留同一位成年主体、可识别的面部身份、手托腮姿势、抬起的肘部、坐在车内的位置和特写裁剪。应用大胆不透明色、哑光海报颜料质感、粗而自信的轮廓线、简化块面、极少阴影的平涂以及略圆润柔和的比例。面部采用沉重眼睑、图形化翼状眼线、细长拱眉、单一曲线勾勒的长细鼻子和闭嘴微笑的小嘴;使用温暖桃色肤色与实心玫瑰粉圆形腮红,不要雀斑、点状或纹理化腮红。车内保持扁平深蓝色,座椅和门板加入白色虚线缝线。窗外保留参考图背景的位置关系,并将其中的小红车、微笑司机、黄色太阳、蓝色轮廓扇形云、叶子、心形和花朵风格化。人物上方的负空间置于奶油色背景,填入星星、小枝、圆点、拱形和一朵花等民俗图案。使用高饱和桃色、芥末黄、珊瑚粉、棕色、深蓝、天蓝、紫色和绿色,全程无渐变。排除写实摄影、3D、可读文字、标志、水印和身份改变。
English prompt
Transform the uploaded identity reference photo into a stylized flat folk-art gouache and marker illustration without inventing a new scene. Preserve the same adult subject, recognizable facial identity, cheek-on-hand pose, raised elbow, seated position inside the car, and close-up crop. Apply bold opaque colors, a matte poster-paint finish, thick confident outlines, simplified blocky shapes, flat fills with minimal shading, and softly rounded proportions. Render the face with heavy-lidded eyes, graphic winged eyeliner, thin arched brows, a long thin nose drawn with one curved line, and small closed smiling lips; use warm peach skin with solid rosy-pink circular cheeks, no freckles, and no texture stippling. Keep the car interior flat navy with dashed white stitch details. Through the window, preserve the reference's background placement while stylizing any simplified red car, smiling driver, yellow sun, blue-outlined scalloped clouds, leaves, hearts, and flowers. Fill upper negative space with cream-ground folk motifs: stars, sprigs, dots, arches, and a flower. Use a saturated palette of peach, mustard, coral, brown, navy, sky blue, purple, and green with no gradients. No photorealism, 3D, readable text, logos, watermarks, or altered identity.
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