Moda de pasarela con mascotas de peluche

【主体】，成年人真人化，怪萌吉祥物时装 × 毛绒潮玩角色 × 暗黑童趣 editorial 摄影。

主体为成年真人模特，脸部保持清楚的人类结构，带轻微吉祥物化处理。整体保持玩偶式瘦长比例：头部略大、肩窄、脖子短、躯干细长、四肢纤细修长。不同动作中始终保留木讷、僵直、笨拙的人形玩偶感。

服装由模型自主设计为动物或幻想小兽主题的毛绒 mascot fashion。耳朵、尾巴、胸前图形、袖套、手套、圆头鞋、局部脸部图形与材质拼接自由变化。材质以毛绒、羊羔绒、抓绒、针织、软泡棉为主，轮廓简洁，触感蓬松。主体由 2–4 个主色色块构成，局部加入高饱和跳色。

动作与表情随机设计，可从前倾、探身、歪头、回头、扭转、踮脚、抬手、张开双臂、伸手、迈步、半蹲、俯身、单脚抬起或轻微跳起等方向展开，并创造新的动作组合。动作具有明确张力，保留玩偶式僵硬、失衡与不协调的幽默感。表情在无辜、冷淡、发愣、轻微惊讶、呆滞、笨拙认真之间变化。

镜头与构图由模型根据动作自主设计，景别可为全身、近中景或近距离全身；机位可为平视、轻微低机位、近距离轻广角或自然棚拍视角。人物位置、身体朝向、透视、裁切与留白随动作变化，动作方向与画面空间相互呼应，清楚呈现细长比例和服装轮廓。

背景采用纯白、浅灰、低饱和纯色或简洁棚拍色场。光线干净柔和，强调毛绒材质、人物轮廓与姿态。整体兼具角色设定图与表演性时装摄影的视觉特点。

批量生成时，每张自主变化动物主题、服装结构、配色、动作、表情、身体朝向、景别、机位与构图，保持统一的身体比例与视觉基调。

3:4 竖图，右下角小型“voxcat”签名。

[Subject], adult human-like adaptation, quirky mascot fashion × plush designer toy character × dark playful editorial photography.

The subject is an adult real-person model, retaining clear human facial structure with subtle mascot styling. The overall body retains an elongated doll-like proportion: slightly large head, narrow shoulders, short neck, slender torso, and slim elongated limbs. Consistently retains the wooden, stiff, clumsy feel of a humanoid doll across various poses.

Outfits are autonomously designed by the model as animal or mythical creature-themed plush mascot fashion. Ears, tails, chest patterns, arm warmers, gloves, round-toe shoes, localized facial patterns, and material patchwork vary freely. Materials predominantly feature plush, shearling fleece, polar fleece, knitwear, and soft foam, with clean silhouettes and fluffy texture. Color palette consists of 2–4 primary blocks with occasional high-saturation accent pops.

Posing and expressions are randomly generated, exploring leaning forward, peering, tilting head, looking back, twisting, tiptoeing, raising arms, outstretching hands, stepping, crouching, bowing, raising one foot, or subtle jumping, creating novel pose combinations. Movements carry distinct tension while preserving the doll-like stiffness, unbalance, and clumsy humor. Expressions range between innocent, aloof, dazed, slightly surprised, blank, and awkwardly earnest.

Camera angle and composition are autonomously determined based on movement; framing can be full-body, medium-close, or close-up full-body; angles can be eye-level, low angle, close-up wide-angle, or natural studio perspectives. Composition, perspective, crop, and negative space adapt dynamically to present the slender proportions and furry silhouette clearly.

Background uses pure white, light gray, muted solid color, or a minimal studio color field. Clean, soft lighting accentuates plush textures, silhouettes, and postures. Balanced between character sheet aesthetics and performative fashion editorial photography.

When batch generating, autonomously vary the animal theme, garment structure, color scheme, pose, expression, facing, shot type, angle, and composition while preserving consistent body proportions and visual tone.

3:4 aspect ratio, small "voxcat" signature in bottom right corner.