Generate realistic on-model fashion photos from your garment/accessory references and an optional model photo.
| Base Model | Pricing Mode | Effective Cost |
|---|---|---|
| nano-bananadefault | per output | $0.039 |
Clothes on Model is a image-to-image AI wrapper by modelrunner. On ModelRunner it runs through a REST API or via MCP from any AI assistant with pay-per-use pricing.
# Submit a request to the queue. Input fields go at the top level of the
# body. The optional reserved "metadata" object holds your own flat string
# tags — stored on the request, never sent to the model; filter later with
# GET https://queue.modelrunner.run/requests?metadata=<url-encoded JSON>.
curl -X POST https://queue.modelrunner.run/modelrunner/clothes-on-model \
-H "Authorization: Key $MRUN_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"hat_image": "https://media.modelrunner.ai/YCzpHPF8RLQRM5Xu-hat.webp",
"top_image": "https://media.modelrunner.ai/VGx9FxtChQ3WD41W-tshirt-2.webp",
"shoe_image": "https://media.modelrunner.ai/J4vvUeomPe9JpPrl-shoes.jpeg",
"environment": "lake side",
"model_image": "https://media.modelrunner.ai/nFrUaBDrQ9AJcc9c-woman-model.webp",
"num_outputs": 3,
"aspect_ratio": "9:16",
"bottom_image": "https://media.modelrunner.ai/xE4aCKZYmbxeybMg-bottom.png",
"metadata": {
"project": "my-project"
}
}'
# → { "request_id": "...", "status_url": "...", "response_url": "..." }
# Poll status_url until "COMPLETED", then fetch the result
curl "https://queue.modelrunner.run/modelrunner/clothes-on-model/requests/$REQUEST_ID/status" \
-H "Authorization: Key $MRUN_API_KEY"
curl "https://queue.modelrunner.run/modelrunner/clothes-on-model/requests/$REQUEST_ID" \
-H "Authorization: Key $MRUN_API_KEY"import { modelrunner } from "@modelrunner/client";
const result = await modelrunner.subscribe("modelrunner/clothes-on-model", {
input: {
"hat_image": "https://media.modelrunner.ai/YCzpHPF8RLQRM5Xu-hat.webp",
"top_image": "https://media.modelrunner.ai/VGx9FxtChQ3WD41W-tshirt-2.webp",
"shoe_image": "https://media.modelrunner.ai/J4vvUeomPe9JpPrl-shoes.jpeg",
"environment": "lake side",
"model_image": "https://media.modelrunner.ai/nFrUaBDrQ9AJcc9c-woman-model.webp",
"num_outputs": 3,
"aspect_ratio": "9:16",
"bottom_image": "https://media.modelrunner.ai/xE4aCKZYmbxeybMg-bottom.png"
},
});
console.log(result);import os
import requests
headers = {"Authorization": f"Key {os.environ['MRUN_API_KEY']}"}
submitted = requests.post(
"https://queue.modelrunner.run/modelrunner/clothes-on-model",
headers=headers,
json={
"hat_image": "https://media.modelrunner.ai/YCzpHPF8RLQRM5Xu-hat.webp",
"top_image": "https://media.modelrunner.ai/VGx9FxtChQ3WD41W-tshirt-2.webp",
"shoe_image": "https://media.modelrunner.ai/J4vvUeomPe9JpPrl-shoes.jpeg",
"environment": "lake side",
"model_image": "https://media.modelrunner.ai/nFrUaBDrQ9AJcc9c-woman-model.webp",
"num_outputs": 3,
"aspect_ratio": "9:16",
"bottom_image": "https://media.modelrunner.ai/xE4aCKZYmbxeybMg-bottom.png"
},
).json()
# Poll submitted["status_url"] until "COMPLETED", then:
result = requests.get(submitted["response_url"], headers=headers).json()| Name | Type | Required | Description |
|---|---|---|---|
| environment | enum | no | Scene/background environment. One of: environment of model, forest, lake side, studio, desert, rocky sea side, rocky mountain, beach. Default: "environment of model". |
| model_image | string (uri) | no | Optional model/person reference image. Supports public URLs or data URIs. |
| hat_image | string (uri) | no | Optional hat reference image. Supports public URLs or data URIs. |
| shoe_image | string (uri) | no | Optional shoe reference image. Supports public URLs or data URIs. |
| top_image | string (uri) | no | Optional top (shirt, blouse, etc.) reference image. Supports public URLs or data URIs. |
| bottom_image | string (uri) | no | Optional bottom (pants, skirt, etc.) reference image. Supports public URLs or data URIs. |
| dress_image | string (uri) | no | Optional dress reference image. Supports public URLs or data URIs. |
| num_outputs | integer | no | The number of images to generate. Default: 1. |
| prompt | string | no | Optional additional prompt to refine the clothes-on-model result. |
| image_size | string (image-size) | yes | Select the aspect ratio and resolution for the generated image |
Machine-readable: OpenAPI schema · llms.txt
Point Claude Code, Claude Desktop, Cursor, or any MCP client at the ModelRunner MCP server and Clothes on Model becomes a tool your assistant can call directly — it authorizes via OAuth (no API key in config) and runs this wrapper with the run_model tool using the endpoint modelrunner/clothes-on-model.
{
"mcpServers": {
"modelrunner": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://mcp.modelrunner.run/mcp"]
}
}
}claude mcp add --transport http modelrunner https://mcp.modelrunner.run/mcpThen ask your assistant, for example: “Run modelrunner/clothes-on-model on ModelRunner to generate image”. MCP setup guide.
Clothes-on-Model composes believable, on-model product photos for fashion catalogs and listings. Supply reference images for garments and accessories (and optionally a model photo). The system renders accurate fit, drape, and scale while preserving product design and color.