OpenZhenZhen AI 提示词画廊 · gpt-image-2.5 · image
绯红线绣亚麻写实艺术肖像
Crimson Embroidered Linen Realistic Portrait
将输入肖像转化为绣在天然米色粗亚麻布上的写实纺织艺术：以深猩红、宝石红和绯红绣线表现面部细节与蓬松发丝，呈现清晰针脚、织物纹理和立体线绣。居中构图，肖像下方垂落数根红线并连接一枚木侧边深红线轴，左上方柔和暖光，竖版3:4。
提示词 / Prompt
中文提示词
将 ref-10a-v1 固定人物身份参考图（默认值：ref-10a-v1 固定人物身份参考图）转化为一幅直接绣在天然米色粗亚麻布或麻布上的写实纺织肖像。保留主体可辨识的面部身份、比例和自然表情；不要美化、卡通化或改变面部。整幅肖像完全以清晰可见的深猩红、宝石红和绯红色绣线构成：用细密且顺应形体方向的针脚，以及不同粗细、密度的分层线迹，表现面部轮廓、眼睛、眉毛、睫毛、鼻子、嘴唇、颧骨和阴影。将头发表现为蓬松的红色线束，带有自然波浪或卷曲、飞散纤维、交叠环线和可信的凸起立体感；若主体有面部毛发，则用细小独立红纤维表现，并顺着自然生长方向排列。清晰呈现亚麻织纹、细微不规则、线张力、独立针脚、微微凸起的刺绣和细腻接触阴影，让线与布料呈现有触感的高光和阴影。采用居中优雅构图，让头部和头发占据画面大部分。几根松散红线从肖像下缘垂落，连接到位于颈部正下方、带木质端盖的小型深红线轴；另有一根线在布面轻轻卷曲。使用左上方柔和温暖的棚拍光、轻柔方向性阴影和线纤维上的微妙高光，呈现微距纺织摄影质感。竖版3:4构图，完整呈现肖像和线轴，背景为天然米色布料；红线只用于肖像。不要墨水、油漆、铅笔、印刷轮廓、数字插画、普通照片质感的面部皮肤、排版文字、水印、边框或额外装饰物。材质应可信、构图干净；极致细节仅作审美方向，不承诺具体分辨率。
English prompt
Transform ref-10a-v1 固定人物身份参考图 (default: ref-10a-v1 固定人物身份参考图) into a photorealistic textile portrait stitched directly onto coarse natural beige linen or burlap. Preserve the subject's recognizable facial identity, proportions and natural expression; do not beautify, cartoonize or alter the face. Recreate the portrait entirely with individually visible deep scarlet, ruby and crimson embroidery threads: use fine directional stitches and layered thread lines of varied thickness and density to define facial contours, eyes, brows, lashes, nose, lips, cheekbones and shadows. Render the hair as voluminous red thread strands with natural waves or curls, flyaways, overlapping loops and convincing raised depth; if facial hair is present, form it from fine individual red fibers following its natural growth direction. Show woven fabric grain, small irregularities, thread tension, distinct stitches, subtle raised embroidery and delicate contact shadows; make thread and linen interact with tactile highlights and shadows. Center an elegant portrait with the head and hair filling most of the frame. Let a few loose red strands trail from the portrait's lower edge to a small deep-red thread spool with wooden end caps directly below the neck; include one strand curling gently across the fabric. Light the scene with soft warm studio light from the upper left, gentle directional shadows and subtle fiber highlights, in a macro textile-photography aesthetic. Vertical 3:4 composition with the full portrait and spool visible against natural beige fabric. Use red thread for the portrait only. No ink, paint, pencil, printed outlines, digital illustration, ordinary photographic skin, typography, lettering, watermark, border or extra decorative objects. Keep the materials physically believable and the composition clean; treat exceptional detail as an aesthetic direction, not a technical-resolution guarantee.
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
- 莱雷海滩黄金时刻电影感人像
泰国莱雷海滩黄金时段的超写实电影感齐腰旅拍肖像：以当前配置固定参考 ref-10a-v1 明确绑定模板中的第一人称“我”，人物穿宽松米白亚麻衬衫、经典太阳镜和简约腕表；背景为石灰岩悬崖及柔和虚化的碧绿安达曼海。完整保留自然发型、暖色肤调、海风、无修图质感及 85 mm 摄影要求。 | An ultra-realistic cinematic waist-up travel portrait at Railay Beach, Thailand: the currently configured fixed reference ref-10a-v1 is explicitly bound to t
- 吃我一脚
Photorealistic professional e-commerce photography, extreme low-angle frontal perspective directly facing the model's barefoot raised foot, the large sole and pointed toes fill the foreground with strong foreshortening, dramatic near-to-far perspective and visual pressure, elegant young woman with l
- 1
让材质更加干净整洁一些
- 漫步欧洲街头的三格时尚画报
垂直三格欧洲街拍时尚拼贴：以 ref-10a-v1 作为此可复用模板中女性主体的唯一面部身份参考；完整呈现街景、三种抓拍视角、服饰与配件、冰咖啡自拍及 Linkin Park 音乐播放器。面部特征按参考尽量保留，生成可能存在自然差异；64K 是高分辨率目标，不承诺实际像素尺寸。 | A vertical three-panel European street-style fashion collage using ref-10a-v1 as the sole facial identity reference for the female subject in this reusable te
- 俯拍夜幕下的便利店街头肖像
夜间街头时尚抓拍：从街对面较高楼层向下拍摄，一名年轻女子独自站在小型超市入口附近，略微偏离中心，呈现全身并保留开阔留白；穿白色 T 恤、水洗蓝色牛仔夹克、深色直筒牛仔裤和白色帆布运动鞋，单肩挂小手提袋。使用当前配置的固定面部参考 ref-10a-v1 作为本模板人物的面部参考。 | Candid night street-fashion scene viewed downward from an upper floor across the street: a young woman stands alone near a minimarket entrance, slightly off-c
- 最喜欢的角色进食动作
Add a food-specific eating action to the character in the configured reference image. Food is editable; defaults to a strawberry. The source mentions Nano Banana as its tool context. / 为配置参考图中的角色添加指定食物的进食动作；食物可编辑，默认一颗草莓。来源将 Nano Banana 作为工具语境提及。