Annotated Outfit Breakdown
Create outfit collages with callout arrows
Annotated Outfit Breakdown
Create outfit collages with callout arrows
Showcase
单品标注箭头拆解
穿搭拆解图 · 单品标注箭头
单品标注箭头拆解
穿搭拆解图 · 单品标注箭头
Description
Turn a single outfit photo into a clear, easy-to-read outfit breakdown image—ideal for outfit sharing, fashion editing, styling records, and social media posts. The image preserves the person’s facial features, pose, and original outfit, while separating the jacket, top, bottoms, shoes, and visible accessories into individual product-style item images arranged naturally around the centered subject, making the full look easy to understand at a glance. Each item is labeled with handwritten doodle-style text and curved arrows that accurately identify its color, category, and material. Brand information is included only when you provide it and is never guessed. The overall design combines a warm off-white paper background, soft watercolor blocks, and a few hand-drawn symbols with a realistic person and clean item images, creating a relaxed, editorial collage effect while avoiding obstruction of the subject or inventing clothing that does not appear in the original photo. You can also adjust the label language, item-image style, color palette, number of items, and aspect ratio to better match your personal taste and publishing context.
Recommended by
淡苍
Why we love this skill
Turns an outfit photo into an organized, editorial-style breakdown collage with preserved details, individually reconstructed items, handwritten labels, and curved arrows.
Related Skills
View all
ImageWatercolor Urban Fashion
Turn a person, outfit, urban setting, or creative theme into a watercolor, hand-painted fashion illustration concept ready for image generation. It focuses on a relaxed, confident, and artistic urban aesthetic, combining slightly elongated, exaggerated fashion-illustration proportions, richly layered casual outfits, bright and warm colors, and everyday props such as coffee cups, bouquets, books, pets, and shopping bags. These elements create a light, natural sense of story between the person and their surroundings. You’ll receive clear character and scene settings, complete Chinese prompts for image generation, negative prompts, and composition suggestions suited to different uses. The artwork emphasizes watercolor or gouache color blocks, ink linework, colored-pencil or marker textures, natural bleeding, paper grain, and a handmade warmth, while also allowing for the generous negative space of a journal page or illustration card. Chinese copy provided by the user can be naturally integrated into the image; when none is provided, the tool can add a short handwritten-style phrase based on the theme. Urban women, men, nonbinary people, and adult fashion figures of unspecified gender can all be created according to the request. This Skill is suited to fashion illustrations, social media graphics, phone or computer wallpapers, illustration cards, and lifestyle visual concepts. Ordinary portraits, photorealistic people, and complex cinematic scenes are outside its primary use.
ImageStreet Style Flash Prompts
Generate image prompts for streetwear, bags, shoes, and other accessories with the candid feel of close-up direct flash. Keep products clear and eye-catching while preserving the relaxed poses and immediate snapshot atmosphere of a real street setting. Ideal for brand visuals, social media content, and early-stage fashion and accessory concept images, without turning the scene into stiff, formal studio photography or an overly polished advertising campaign. You can provide a single product, a person’s outfit, or a specific use case, along with colors, materials, quantity, carrying method, and aspect ratio. The skill builds each scene around close-range front-facing flash, short hard shadows, darker but still discernible ambient exposure, and street backgrounds in natural gray, white, deep blue, and other tones. It also adjusts the composition for different relationships, such as hand-carrying, crossbody wear, or placing an item on a table, making bag bodies, handles, soles, and garment structure easier to see. The default output includes standalone 16:9 visual concepts and prompts ready for use with Midjourney and Chinese ImageGen. If you need only one format, you can request it. For multi-image series, it can also maintain consistent product features and visual style while varying the settings and poses, making it suitable for building a cohesive street fashion image series.
ImagePersonal Brand Fashion Poster
Turn a portrait and personal profile into a fashion-forward visual poster with a distinctive personal brand identity. Whether you provide a real photo or a cartoon character, it can serve as the subject reference. By combining your name, profession, keywords, philosophy, notable experiences, desired tone, and brand details, the Skill creates a more editorial and stylish personal image. When key information is missing, it first helps confirm the details instead of inventing titles, numbers, or achievements. The poster centers on the subject and extends their positioning into a complete visual world. Oversized Chinese typography, modernist fonts, airport wayfinding elements, and route-map-like line systems create visual connections between the person, brand name, profession, and theme. Rather than simply placing the subject in the center of a background, it integrates them into the typography and graphic structure through a high-end fashion photography approach, with a natural, intelligent, and slightly bold look and pose. It is suitable for creators, designers, consultants, entrepreneurs, culture professionals, and personal brands. You can specify the brand colors, on-image text, whether to preserve the portrait’s recognizability, and the output ratio. If no colors are provided, the primary color scheme is determined based on your field, personality, theme, and audience. The final deliverable is a vertical personal brand poster primarily in Chinese, optionally paired with brief English information, along with the reasoning behind the chosen primary colors, the core text, the personal information extracted, and the direction for the subject’s styling.
Information
- Version
- v3
- Last updated
- Runtime credits
- Usage-based
- Models
- Auto
