Virtual Try-On — See yourself in any outfit

Tools / Virtual Try-On

Try On

Upload a person photo and a garment photo to generate the person wearing that clothing. Works with tops, bottoms, dresses, and full outfits.

Returns: Image of the person wearing the garment, downloadable asset, and shareable page link

Parameters

person_image *stringURL of the person photo. The tool server CAN fetch any public URL — always pass it. Should show upper or full body.

garment_image *stringURL of the clothing/garment photo. Flat-lay or on-mannequin photos work best. The tool server CAN fetch any public URL.

modelstringTry-on model to use. Default: fashn (best quality).

categorystringGarment category. FASHN only. Default: auto (auto-detect).

modestringQuality vs speed tradeoff. FASHN only. Default: balanced.

garment_photo_typestringType of garment photo. FASHN only. Default: auto.

num_samplesnumberNumber of result variations (1-4). FASHN only. Default: 1.

preserve_posebooleanPreserve the person original pose. Quick model only. Default: true.

aspect_ratiostringOutput aspect ratio. Quick model only. Default: 3:4.

garment_typestringGarment type. Leffa only. Required for Leffa. Default: upper_body.

cloth_typestringClothing type. CAT-VTON only. Default: upper.

num_inference_stepsnumberNumber of inference steps (1-50). Leffa and CAT-VTON only. Higher = better quality, slower.

guidance_scalenumberGuidance scale (0-20). Leffa and CAT-VTON only. Higher = stronger garment adherence.

seednumberRandom seed for reproducible results.

output_formatstringOutput image format. FASHN and Leffa only. Default: png.

Example

Try on a shirt

curl -H "Authorization: Bearer $TOOLROUTER_API_KEY" \
  -d '{
  "tool": "virtual-tryon",
  "skill": "try_on",
  "input": {
    "person_image": "https://example.com/person.jpg",
    "garment_image": "https://example.com/shirt.jpg"
  }
}' \
  https://api.toolrouter.com/v1/tools/call

List Models

List all available virtual try-on models with pricing, quality details, supported garment categories, and licensing info.

Returns: All available virtual try-on models with pricing, quality, categories, and licensing

Example

List all try-on models

curl -H "Authorization: Bearer $TOOLROUTER_API_KEY" \
  -d '{
  "tool": "virtual-tryon",
  "skill": "list_models",
  "input": {}
}' \
  https://api.toolrouter.com/v1/tools/call

Quick Start

MCP (Claude Code)

claude mcp add --transport stdio \
  --env TOOLROUTER_API_KEY=YOUR_API_KEY \
  toolrouter -- npx -y toolrouter-mcp

REST API

curl -H "Authorization: Bearer $TOOLROUTER_API_KEY" \
  -d '{"tool":"virtual-tryon","skill":"try_on","input":{}}' \
  https://api.toolrouter.com/v1/tools/call

Frequently Asked Questions

What photos work best for a try-on?

Use a full or upper-body person photo with the clothing area visible, plus a flat-lay or mannequin garment photo.

Can it handle tops, bottoms, dresses, and full outfits?

Yes. The tool supports all of those garment types.

Which model should I choose?

`fashn` is the best-quality default, `quick` is the cheapest preview, `kolors` is the middle ground, `leffa` adds explicit garment control, and `catvton` is research-only.

Can I compare models before I try a look?

`list_models` shows the available models with pricing, quality, supported garment categories, and licensing info.