竖版双拼原图与构成主义重构

Create a full vertical split-style illustration, with the canvas strictly in a vertical composition, divided equally top and bottom at a 1:1 ratio, forming a clear visual contrast: the top is a refinement of the original image subject, and the bottom is a Constructivist style reconstruction.

Upper part:
Use the uploaded original image as the sole subject reference source, automatically identify and extract the subject such as people, cats, dogs, or other pets, without taking buildings or the environment as the main content. Try to preserve the core identifying features of the subject, including the person's face shape, features, hairstyle, clothing, and sense of age, or the pet's fur color, patterns, face shape, ears, and body shape. The background can be simplified; the subject should be clear, the composition stable, and not subject to meaningless cropping.

Lower part:
Transform the same subject into a full illustration in the visual language of "Constructivism." Core style features: red, black, cream-white, diagonal composition, geometric cutting, and strong propaganda poster rhythm. Overall principles: adopt clear geometric structures, flat planes, and ordered composition, controlling hierarchy and white space. The composition uses a single clear subject or a clear scene, the visual center is stable, the subject is complete and not cut off, and the background is moderately simplified while retaining a sense of breathing; lines, color blocks, light and shadow, materials, and paper texture must serve the same style, without mixing in irrelevant art styles. Integrate the subject's posture, gaze, or movement into a strong diagonal composition, using geometric cutting, diagonal power, propaganda-style tension, and a limited color system to reconstruct the image, giving it a clear Constructivist visual rhythm. The image should be natural, have a handmade feel and recognizable style features, avoiding common AI issues like excessive smoothness, meaningless piles of detail, and random decoration.

Overall requirements:
The top and bottom parts are the visual transformation of the same subject before and after; the bottom part should have a distinct sense of Constructivist power and a propaganda poster atmosphere, but do not generate text, logos, watermarks, borders, or UI, and do not create multi-image collages.

创作一张竖版上下双拼风格的完整插画，画布严格竖向构图，上下对半分割，各占 1:1，形成清晰的视觉对照：上方为原图主体提炼，下方为构成主义风格重构。
上半部分：
以上传原图作为唯一主体参考来源，自动识别并提取人物、猫、狗或其他宠物主体，不以建筑或环境为主要表现内容。尽量保留主体的核心识别特征，包括人物的脸型、五官、发型、服饰与年龄感，或宠物的毛色、花纹、脸型、耳朵、体型等。背景可做简化处理，主体清晰，构图稳定，不被无意义裁切。
下半部分：
将同一个主体转化为「Constructivism 构成主义」视觉语言的完整插画。核心风格特征：红黑米白、斜向构图、几何切割和强烈宣传画节奏。整体原则：采用清晰的几何结构、平面块面与秩序化构图，控制层级和留白。构图采用单一明确主体或一个清晰场景，视觉中心稳定，主体完整不被裁断，背景适度简化并保留呼吸感；线条、色块、明暗、材质和纸面纹理必须服务于同一风格，不混入无关画风。将主体姿态、视线或动作融入强烈的斜向构图之中，用几何切割、对角力量、宣传画式张力和有限色彩系统来重建画面，使其具有明确的构成主义视觉节奏。画面自然、有手作感和可识别的风格特征，避免 AI 常见的过度光滑、无意义细节堆砌和随机装饰。
整体要求：
上下两部分是同一主体的前后视觉转化，下半部分应具有鲜明的构成主义力量感和宣传画气息，但不生成文字、Logo、水印、边框、UI，不做多图拼接。