Thư viện prompt AI OpenZhenZhen · gpt-image-2.5 · image

Poster đối chiếu chân dung chính diện và bóng silhouette không gian âm khái niệm

Frontal Portrait and Conceptual Negative Space Silhouette Contrast Poster

Poster đối chiếu chân dung chính diện và bóng silhouette không gian âm khái niệm — khám phá tác phẩm được tạo bằng gpt-image-2.5 trên OpenZhenZhen, kèm prompt gốc và ví dụ tạo nội dung để tham khảo.

Poster đối chiếu chân dung chính diện và bóng silhouette không gian âm khái niệm — AI image creation
Poster đối chiếu chân dung chính diện và bóng silhouette không gian âm khái niệm

Prompt

Prompt tiếng Trung

将随附 ref-10a-v1 整幅 JPG 作为实际原始照片。制作一张竖向 3:4 上下对比转绘海报，采用克制的“概念留白剪影风”。上部约占画布 42%–48%。完整保留照片中的女性、身份、主体数量、正面姿态、视角、空间关系、光线、材质和可识别色彩。按比例容纳整幅图，不得裁切或扭曲；只允许自然的出版级调色。不得将上半照片插画化、改变地点或增删关键主体。上下之间用干净的暖白接缝分隔，不加粗边框、照片标签或“原图/AI图”角标。 下半部不要复制整幅照片，也不要绘制完整插画。只从这张真实人像中提炼一个有意义的形态：女性静止的正面站姿，以及长发环绕形成的流动外缘。将其重构为一个炭黑、墨黑或深石墨色的抽象平面剪影——一条可回溯至真实轮廓的头发与肩部连贯线形。形态可以拉长、缩小、偏置、旋转、断开或跨越留白，但必须是单一载体，不能变成多个漂浮物。不要描绘面部特征或服装纹理。下半部保持 60%–80% 连续暖白留白，纸面只有极淡纤维与哑光颗粒。形状边缘可有克制的网点或干刷颗粒，但整体须平面、干净、清晰；不做水墨晕染或精细线稿。最多加入一两条极细辅助线提示方向；不得添加第二个抽象形状。 主体形状以炭黑、墨黑或深石墨为主，最多从照片提取一处极低饱和点色，不套用固定蓝色、绿色或城市色板。选用极小英文页脚“ONE GESTURE / OPEN SPACE”，描述单一线形与其周围留白。不要加入大标题、长段落或虚构地点。让上半部承载摄影事实，下半部承载这一单一形态与留白节奏。不得重绘完整场景；不得添加路线节点、天际线、照片窗、彩色几何海报、厚重纸艺、3D 渲染、自动描边、标志、水印、假中文或“原图/AI图”角标。

Prompt tiếng Anh

Use the entire attached ref-10a-v1 JPG as the actual source photograph. Create one vertical 3:4 top-and-bottom comparative transfer poster in a restrained CONCEPTUAL SILHOUETTE VOID style. The upper photo occupies about 42%–48% of the canvas. Preserve the complete photo’s woman, identity, quantity, frontal pose, perspective, spatial relationships, light, material, and recognizable colors. Fit the entire image proportionally without cropping or distortion; allow only natural publishing-level grading. Do not illustrate the upper photo, change its location, or add or remove key subjects. Separate the areas with a clean warm-white seam, without a thick border, photo tag, or Original/AI badge. In the lower area, do not copy the whole photo or draw a complete illustration. Extract just one meaningful form from this actual portrait: the woman’s still frontal stance framed by the long sweep of her hair. Reconstruct this as one charcoal-black, ink-black, or dark-graphite abstract flat silhouette—a single flowing hair-and-shoulder contour that remains traceable to her real outline. It may be elongated, reduced, offset, rotated, interrupted, or span the negative space, but must remain one carrier, not multiple floating objects. Do not depict facial features or clothing texture. Keep 60%–80% of the lower area as continuous warm-white negative space with only very faint paper fibers and matte grain. The shape may have restrained edge halftone or dry-brush grain, but stay flat, clean, and crisp; no ink wash or fine line art. At most one or two extremely fine auxiliary lines may suggest direction; add no second abstract shape. Use charcoal/ink/graphite as the main shape color and at most one extremely low-saturation accent sampled from this photo, with no fixed blue, green, or city palette. Choose the tiny English footer “ONE GESTURE / OPEN SPACE” to describe the single contour and its surrounding void. Do not add a large title, long text, or fictional location. Let the upper half carry the photographic facts and the lower half carry this single form and negative-space rhythm. Do not redraw the full scene; add no route nodes, skyline, photo window, colored geometric poster, heavy paper art, 3D rendering, automatic outline, logo, watermark, fake Chinese, or Original/AI badges.

Xem mô hình API

Xem thêm prompt hình ảnh và video · Tạo hình ảnh · Tạo video · Tạo trên canvas AI