# IDM VTON

IDM VTON is best-in-class clothing virtual try-on in the wild (non-commercial use only)

## API Information

- **Model Slug:** idm-vton
- **Branded URL:** https://www.eachlabs.ai/alibaba/idm-vton/idm-vton
- **Provider:** Alibaba
- **Category:** Image to Image
- **Output Type:** image
- **Status:** active
- **Version:** 0.0.1
- **Base Cost:** Per-second pricing based on provider predict_time. Rate: $0.00154/sec from GPU tier.
- **Estimated Processing Time:** 26 seconds
- **Last Updated:** 2026-04-06
- **Interactive Demo:** https://www.eachlabs.ai/ai-models/idm-vton

## Pricing

- **Charge Type:** dynamic
- **Pricing Details:** Per-second pricing based on provider predict_time. Rate: $0.00154/sec from GPU tier.

### Pricing Rules

| Condition | Pricing |
| --- | --- |
| Rule 1 | Per-second pricing based on provider predict_time. Rate: $0.00154/sec from GPU tier. |

## Input Schema

| Parameter | Type | Required | Default | Constraints | Description |
|-----------|------|----------|---------|-------------|-------------|
| garm_img | string | Yes | https://storage.googleapis.com/magicpoint/inputs/clothes-change-input-2.webp | image/jpeg, image/png, image/jpg, image/webp | Garment, should match the category, can be a product image or even a photo of someone |
| garment_des | string | No | - | - | Description of garment e.g. Short Sleeve Round Neck T-shirt |
| human_img | string | Yes | - | image/jpeg, image/png, image/jpg, image/webp | Model, if this is not 3:4 check crop |
| mask_img | string | No | - | image/jpeg, image/png, image/jpg, image/webp | Mask image, optional (but faster) |
| category | string | No | upper_body | upper_body,lover_body,dresses | An enumeration. |
| crop | boolean | No | true | - | A 'crop' is a trimming technique where unwanted outer areas of an image are removed, focusing on the most important part. |
| force_dc | boolean | No | false | - | Use the DressCode version of IDM-VTON (this is default false, except if category=dresses) |
| mask_only | boolean | No | false | - | Return only the mask |
| steps | integer | No | 30 | 0–40 | - |
| seed | integer | No | 42 | - | - |

## Example Request

```bash
curl -X POST https://api.eachlabs.ai/v1/prediction/ \
  -H "X-API-Key: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "idm-vton",
  "input": {
    "garm_img": "https://storage.googleapis.com/magicpoint/inputs/clothes-change-input-2.webp",
    "human_img": "https://storage.googleapis.com/magicpoint/inputs/idm-vton-human-input.webp"
  }
}'
```

## Output Schema

Response returned by `GET /v1/prediction/{id}` when the job completes:

```json
{
  "status": "success",
  "predictionID": "string",
  "output": "string (URL of generated image)",
  "metrics": {
    "predict_time": "number (seconds)"
  }
}
```

## Polling

```bash
curl https://api.eachlabs.ai/v1/prediction/{PREDICTION_ID} \
  -H "X-API-Key: YOUR_API_KEY"
```

| Status | Meaning |
|--------|---------|
| `processing` | Still running — poll again |
| `success` | Done — read `output` |
| `error` | Failed — read `message` / `details` |

## Webhook (alternative to polling)

Pass `"webhook_url": "https://your.host/path"` in the create request. Eachlabs POSTs this payload when the job ends:

```json
{
  "exec_id": "prediction-uuid",
  "status": "succeeded",
  "output": "https://...",
  "error": ""
}
```

`status` is `"succeeded"` or `"failed"`. `exec_id` equals the `predictionID` from create. Return 2xx within 30 seconds.

## Errors

Error body: `{ "status": "error", "message": "...", "details": "..." }`

| Code | Meaning |
|------|---------|
| `400` | Invalid input |
| `401` | Missing / invalid `X-API-Key` |
| `404` | Unknown model or prediction id |
| `429` | Rate limit — 100 creates / min, 10 concurrent per key |
| `5xx` | Retry with backoff |

## Overview

**idm-vton — Image-to-Image AI Model**

Transform any photo into a perfect outfit showcase with **idm-vton**, Alibaba's best-in-class clothing virtual try-on model designed for realistic garment swapping in unconstrained real-world settings. Developed as part of the idm-vton family, this image-to-image AI model excels at preserving garment details, human poses, and body shapes without requiring controlled studio conditions—ideal for "AI virtual try-on" searches. Whether you're testing fashion designs or visualizing customer looks, idm-vton delivers photorealistic results that outperform traditional methods, making it a go-to for "virtual clothing try-on AI".

Powered by advanced diffusion models, idm-vton handles diverse clothing items like dresses, jackets, and accessories, supporting inputs up to 1024x768 resolution for sharp, high-fidelity outputs. Users love its ability to work with casual smartphone photos, as seen in community examples where wrinkled shirts or patterned fabrics render flawlessly.

## Usage Notes

- API Base URL: `https://api.eachlabs.ai/v1`
- Authentication: send `X-API-Key: YOUR_API_KEY`. Generate a key from the Eachlabs dashboard at https://www.eachlabs.ai/dashboard/api-keys.
- File-typed parameters (`*_url`, `image_url`, `video_url`, `audio_url`, etc.) accept publicly-reachable HTTPS URLs only. Upload your asset first (GCS / S3 / your CDN) and pass the resulting URL. Data-URIs and localhost URLs are rejected.
- For structured parameters (arrays / objects) send real JSON values, not stringified payloads.
- Monetary values are reported in USD; per-token / per-megapixel rates may be billed in micro-cents internally.
- Prefer `webhook_url` over polling for long-running predictions — see the Webhook Callback section.