> ## Documentation Index
> Fetch the complete documentation index at: https://apidoc.cometapi.com/llms.txt
> Use this file to discover all available pages before exploring further.
# Create a Kling virtual try-on
> Use CometAPI Kling Virtual Try-On API to create a try-on image from a person image and clothing image.
Use this endpoint to generate a virtual try-on image from one person image and one garment image.
## Before you call it
* Provide one `human_image` and one `cloth_image`
* Start with `kolors-virtual-try-on-v1` or `kolors-virtual-try-on-v1-5`
* Use clean clothing product shots or white-background garment images for the first test
## Task flow
Send the person image and clothing image, then save the returned task id.
Poll the matching Kling image query path until the task reaches a terminal state and returns the rendered image.
Save the finished image into your own storage if the try-on result needs longer retention.
For the complete parameter reference, see the [official Kling documentation](https://kling.ai/document-api/api/image/virtual-try-on).
## OpenAPI
````yaml api/openapi/image/kling/post-virtual-try-on.openapi.json POST /kling/v1/images/kolors-virtual-try-on
openapi: 3.1.0
info:
title: Kling Virtual Try-On API
version: 1.0.0
servers:
- url: https://api.cometapi.com
security:
- bearerAuth: []
paths:
/kling/v1/images/kolors-virtual-try-on:
post:
summary: Create a Kling virtual try-on
operationId: kling_virtual_try_on
parameters:
- name: Content-Type
in: header
required: false
description: Must be `application/json`.
schema:
type: string
default: application/json
requestBody:
required: true
content:
application/json:
schema:
type: object
required:
- human_image
- cloth_image
properties:
model_name:
type: string
description: >-
Virtual try-on model version. Defaults to
`kolors-virtual-try-on-v1`.
enum:
- kolors-virtual-try-on-v1
- kolors-virtual-try-on-v1-5
default: kolors-virtual-try-on-v1
human_image:
type: string
description: >-
Person image to dress. Image URL or raw Base64 string
without a `data:` prefix. Supported formats: JPG, JPEG, PNG.
Maximum 10 MB, minimum 300x300 px, aspect ratio between
1:2.5 and 2.5:1.
cloth_image:
type: string
description: >-
Clothing image for the try-on. Image URL or raw Base64
string without a `data:` prefix. Supported formats: JPG,
JPEG, PNG. Maximum 10 MB, minimum 300x300 px, aspect ratio
between 1:2.5 and 2.5:1. Supports tops, bottoms, and
one-piece dresses.
callback_url:
type: string
description: Webhook URL for task status notifications.
external_task_id:
type: string
description: >-
Optional user-defined task ID for your own tracking. Must be
unique per account.
default:
model_name: kolors-virtual-try-on-v1
human_image: https://your-image-host/person.jpg
cloth_image: https://your-image-host/garment.jpg
examples:
Default:
summary: Virtual try-on request
value:
model_name: kolors-virtual-try-on-v1
human_image: https://your-image-host/person.jpg
cloth_image: https://your-image-host/garment.jpg
responses:
'200':
description: Task request accepted or an error response returned by the API.
content:
application/json:
schema:
type: object
required:
- code
- message
- data
properties:
code:
oneOf:
- type: integer
- type: string
description: Response code. `0` means the task request was accepted.
message:
type: string
description: Response message.
request_id:
type: string
description: Request identifier returned when present.
data:
type: object
required:
- task_id
- task_status
- created_at
- updated_at
properties:
task_id:
type: string
description: System-generated task ID.
task_status:
type: string
description: Task status.
enum:
- submitted
- processing
- succeed
- failed
task_status_msg:
oneOf:
- type: string
- type: 'null'
description: Task status detail when present.
task_info:
type: object
properties:
external_task_id:
oneOf:
- type: string
- type: 'null'
description: Caller-provided external task ID when supplied.
additionalProperties: true
task_result:
oneOf:
- type: object
additionalProperties: true
- type: 'null'
description: Task result payload after the task completes.
created_at:
type: integer
description: >-
Task creation time as a Unix timestamp in
milliseconds.
updated_at:
type: integer
description: Task update time as a Unix timestamp in milliseconds.
additionalProperties: true
additionalProperties: true
x-codeSamples:
- lang: Shell
label: Default
source: >
curl https://api.cometapi.com/kling/v1/images/kolors-virtual-try-on
\
-H "Authorization: Bearer $COMETAPI_KEY" \
-H "Content-Type: application/json" \
-d '{
"model_name": "kolors-virtual-try-on-v1",
"human_image": "https://your-image-host/person.jpg",
"cloth_image": "https://your-image-host/garment.jpg"
}'
- lang: Python
label: Default
source: |
import os
import requests
response = requests.post(
"https://api.cometapi.com/kling/v1/images/kolors-virtual-try-on",
headers={"Authorization": "Bearer " + os.environ["COMETAPI_KEY"]},
json={
"model_name": "kolors-virtual-try-on-v1",
"human_image": "https://your-image-host/person.jpg",
"cloth_image": "https://your-image-host/garment.jpg"
},
)
result = response.json()
print(result["code"], result.get("data", {}).get("task_id"))
- lang: JavaScript
label: Default
source: >
const response = await
fetch("https://api.cometapi.com/kling/v1/images/kolors-virtual-try-on",
{
method: "POST",
headers: {
Authorization: `Bearer ${process.env.COMETAPI_KEY}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"model_name": "kolors-virtual-try-on-v1",
"human_image": "https://your-image-host/person.jpg",
"cloth_image": "https://your-image-host/garment.jpg"
}),
});
const result = await response.json();
console.log(result.code, result.data?.task_id);
components:
securitySchemes:
bearerAuth:
type: http
scheme: bearer
description: Bearer token authentication. Use your CometAPI key.
````