Skip to content

try-on

Integrate

Model id cat-vton
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://api.doitong.com/v1/run/cat-vton?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "human_image_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg",
    "garment_image_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg",
    "cloth_type": "upper"
  }'

# Still "queued" or "running"? Poll with the id from the response:
curl "https://api.doitong.com/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"

This request: ≈$0.018 18 API credits Run it on this page

Get API key
Open model Image Editing #try-on#fashion#clothing

Virtual try-on that puts a garment image onto a person photo, with selectable clothing type

Open model · Image

Your first result goes here

Build a request below and run it with your API key. Outputs are copied to our storage, kept forever or 7 days for free.

Build a request

Controls are generated from the model schema. The code and the price update as you change them.

•required
Drop a file, or

URL pointing to the image of the person.

•required
Drop a file, or

URL pointing to the garment's image.

cloth_type •required

Garment category for the try-on: upper means upper-body clothing; lower means lower-body clothing; overall means full-body clothing; inner means an inside layer, such as a T-shirt beneath a jacket; outer means an outside layer, such as a jacket covering a T-shirt.

image_size default portrait_4_3

Dimensions of the generated image.

Advanced num_inference_steps · guidance_scale · seed · enable_safety_checker
default 30

Count of inference steps to run.

default 2.5

Prompt-adherence strength for image selection, expressed as CFG (Classifier Free Guidance).

Seed for image reproducibility. Reproducing an image requires keeping the seed, input, and model version unchanged; under those conditions, the result is identical on every run.

POST /run/cat-vton?wait=20 quote → $0.018
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://api.doitong.com/v1/run/cat-vton?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "human_image_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg",
    "garment_image_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg",
    "cloth_type": "upper"
  }'

# Still "queued" or "running"? Poll with the id from the response:
curl "https://api.doitong.com/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"

Run this request

Your key stays in this browser: it is sent only to the Doitong API and saved (localStorage) only if you tick Remember. Get an API key

About try-on

Renders a person wearing a given garment. Requires `human_image_url`, `garment_image_url` and `cloth_type`, which can be upper, lower, overall, inner or outer. Output size uses presets such as portrait_4_3 or square_hd. `num_inference_steps` (1 to 50), `guidance_scale` and a seed are adjustable.

Parameters

NameType DefaultAllowed Description
human_image_urlrequired
Typeurl · image
URL pointing to the image of the person.
garment_image_urlrequired
Typeurl · image
URL pointing to the garment's image.
cloth_typerequired
Typeenum
upperloweroverallinnerouter
Garment category for the try-on: upper means upper-body clothing; lower means lower-body clothing; overall means full-body clothing; inner means an inside layer, such as a T-shirt beneath a jacket; outer means an outside layer, such as a jacket covering a T-shirt.
image_sizeoptional
Typeobject
Defaultportrait_4_3
square_hdsquareportrait_4_3portrait_16_9landscape_4_3landscape_16_9
Dimensions of the generated image.
num_inference_stepsoptional
Typeinteger
Default30
1 – 50
Count of inference steps to run.
guidance_scaleoptional
Typenumber
Default2.5
0 – 20
Prompt-adherence strength for image selection, expressed as CFG (Classifier Free Guidance).
seedoptional
Typeinteger | null
Seed for image reproducibility. Reproducing an image requires keeping the seed, input, and model version unchanged; under those conditions, the result is identical on every run.
enable_safety_checkeroptional
Typeboolean
Defaulttrue
Screening can be relaxed by setting false, provided the caller is authorized.
required

File parameters take a public https:// URL, a data: URI up to 10 MB, or the file_url of an upload. Files

Output

GET /requests/req_8k2m4q7x1z9c3v5b6n0p2r4t
{
  "id": "req_8k2m4q7x1z9c3v5b6n0p2r4t",
  "object": "request",
  "model": "cat-vton",
  "status": "succeeded",
  "created_at": "2026-10-20T12:00:00Z",
  "started_at": "2026-10-20T12:00:02Z",
  "completed_at": "2026-10-20T12:00:09Z",
  "queue_position": null,
  "cost": {
    "credits": 18,
    "usd": "0.018",
    "charged": 18,
    "refunded": 0
  },
  "input": {
    "human_image_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg",
    "garment_image_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg",
    "cloth_type": "upper"
  },
  "output": {
    "image": {
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
      "content_type": "image/jpeg",
      "file_name": "0-output.jpeg",
      "file_size": 1843200,
      "width": 1024,
      "height": 768
    }
  },
  "outputs": [
    {
      "type": "image",
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
      "content_type": "image/jpeg",
      "file_size": 1843200,
      "width": 1024,
      "height": 768,
      "stored": true
    }
  ],
  "error": null,
  "metrics": {
    "inference_seconds": 6.8
  },
  "urls": {
    "self": "https://api.doitong.com/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t",
    "cancel": "https://api.doitong.com/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t/cancel"
  }
}
Your files, your choiceEvery outputs[].url is a copy on our storage: kept forever (paid per GB-month) or 7 days for free, by your account setting or ?storage=.
Same shape on every modeltype, url, content_type, width, height and duration, for images, video and audio alike. output is the model’s own result object.
Fields of output
image
object {url, content_type, file_name, file_size, width, height}Image produced as output.

For AI agents: this page as Markdown is at https://doitong.com/en-US/developers/models/cat-vton.md. All models and guides: https://doitong.com/developers/llms.txt