L’interface est localisée ; les présentations et documents des Skills sont traduits automatiquement par IA dans votre langue. Le code, les commandes, chemins et termes techniques restent en version originale, et le document de l’auteur fait foi.
Explorer les Skills
Productivité · SKILL.md

idm-vton

idm-vton

IDM VTON | Virtual Try-On. Try on clothes virtually by combining a garment image with a person photo. Triggers: virtual try on, vton, clothing try on, garment fitting, try on clothes

Independent GitHub snapshot · Automated classification · Original documentation governs

Documentation de la Skill

GitHub

name: idm-vton description: "IDM VTON | Virtual Try-On. Try on clothes virtually by combining a garment image with a person photo. Triggers: virtual try on, vton, clothing try on, garment fitting, try on clothes" allowed-tools: Bash(curl *), WebFetch

IDM VTON

Virtual try-on that combines a garment image with a person photo. Upload a model photo and a garment image to see how clothes look on the person, supporting upper body, lower body, and dresses.

Quick Start

Requires an each::labs API key. Get one at eachlabs.ai.

curl -X POST https://api.eachlabs.ai/v1/prediction \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -d '{
    "model": "idm-vton",
    "version": "0.0.1",
    "input": {
      "human_img": "https://example.com/model-photo.jpg",
      "garm_img": "https://example.com/tshirt.jpg",
      "garment_des": "Short Sleeve Round Neck T-shirt",
      "category": "upper_body",
      "steps": 30
    }
  }'

Parameters

ParameterTypeDefaultDescription
categorystringupper_bodyGarment category. enum: upper_body, lover_body, dresses
cropbooleantrueCrop the image if not 3:4 aspect ratio
force_dcbooleanfalseUse the DressCode version of IDM-VTON
garm_imgstring-Garment image (product image or photo of clothing)
garment_desstring-Description of garment, e.g., "Short Sleeve Round Neck T-shirt"
human_imgstring-Model/person photo (3:4 aspect ratio recommended)
mask_imgstring-Mask image, optional but speeds up processing
mask_onlybooleanfalseReturn only the mask
seedinteger42Random seed
stepsinteger30Number of generation steps

Examples

Try on a dress:

curl -X POST https://api.eachlabs.ai/v1/prediction \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -d '{
    "model": "idm-vton",
    "version": "0.0.1",
    "input": {
      "human_img": "https://example.com/model-standing.jpg",
      "garm_img": "https://example.com/summer-dress.jpg",
      "garment_des": "Floral print summer dress with v-neck",
      "category": "dresses",
      "crop": true,
      "steps": 30,
      "seed": 42
    }
  }'

Try on pants with mask:

curl -X POST https://api.eachlabs.ai/v1/prediction \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -d '{
    "model": "idm-vton",
    "version": "0.0.1",
    "input": {
      "human_img": "https://example.com/full-body-photo.jpg",
      "garm_img": "https://example.com/jeans.jpg",
      "garment_des": "Slim fit dark blue denim jeans",
      "category": "lover_body",
      "mask_img": "https://example.com/pants-mask.jpg",
      "steps": 30
    }
  }'

Related Models

Documentation

Skills enregistrées