- Introduction
- Quick Start Guide
- Make a request
- Chat Models
- ChatGpt
- ChatGPT (Audio)
- ChatGPT (Chat)
- Chat completion object
- Create chat completion (streaming)
- Create chat completion (non-streaming)
- Create chat image recognition (streaming)
- Create chat image recognition (streaming) base64
- Create chat image recognition (non-streaming)
- Function calling
- N choices
- Create chat function call (only non-streaming)
- Create structured output
- ChatGPT (Completions)
- ChatGPT(Embeddings)
- Anthropic Claude
- Gemini
- Image Models
- MJ
- Ideogram
- Kling Image
- DALL·E 3POST
- Flux (OpenAI dall-e-3 format)POST
- Video Models
- Music Model - Suno
- Illustrate
- Parameter
- Task submission
- Query interface
- Python Samples
- python openai official library (using AutoGPT, langchain, etc.)
- Python uses speech to text
- Python uses text to speech
- Python uses Embeddings
- python calls DALL·E
- python simple call openai function-calling demo
- python langchain
- python llama_index
- Python uses gpt-4o to identify pictures-local pictures
- python library streaming output
- Python uses gpt-4o to identify images
- Plug-in/software usage tutorials
- Help Center
Submit Kolors Virtual Try On
POST
/kling/v1/images/kolors-virtual-try-on
Request
Body Params application/json
human_image
string
required
● Image formats support .jpg / .jpeg / .png
● Image file size cannot exceed 10MB, and image resolution cannot be less than 300*300px
cloth_image
string
optional
Supports inputting images via Base64 encoding or image URL (ensure URL is accessible).
Supported image formats include .jpg / .jpeg / .png.
Image file size must not exceed 10MB, and image resolution must be at least 300x300px.
Specifically, the kolors-virtual-try-on-v1-5 model supports not only single garment input but also combined "top + bottom" garment input, as follows:
Inputting a single garment image (top OR bottom OR one-piece outfit) -> Generates a virtual try-on image for that single item.
Inputting a combined garment image (you can combine multiple single garment white-background images into a single image):
If the model detects "top + bottom" -> Generates a virtual try-on image of the "top + bottom" combination.
If the model detects "top + top" -> Generation fails.
If the model detects "bottom + bottom" -> Generation fails.
If the model detects "one-piece outfit + one-piece outfit" -> Generation fails.
If the model detects "top + one-piece outfit" -> Generation fails.
If the model detects "bottom + one-piece outfit" -> Generation fails.
Example of Combined Garment Images
Example
{
"human_image": "https://gw.alicdn.com/imgextra/i1/1860536677/O1CN012wEzZ11zC7RDNm0Jr_!!1860536677.jpg",
"cloth_image": "https://gw.alicdn.com/imgextra/i4/3370044138/O1CN01p0Zl411gRFvj0NnwQ_!!3370044138.jpg"
}
Request samples
Shell
JavaScript
Java
Swift
Go
PHP
Python
HTTP
C
C#
Objective-C
Ruby
OCaml
Dart
R
Request Request Example
Shell
JavaScript
Java
Swift
curl --location --request POST '/kling/v1/images/kolors-virtual-try-on' \
--header 'Content-Type: application/json' \
--data-raw '{
"human_image": "https://gw.alicdn.com/imgextra/i1/1860536677/O1CN012wEzZ11zC7RDNm0Jr_!!1860536677.jpg",
"cloth_image": "https://gw.alicdn.com/imgextra/i4/3370044138/O1CN01p0Zl411gRFvj0NnwQ_!!3370044138.jpg"
}'
Responses
🟢200Success
application/json
Body
code
integer
required
data
object
required
created_at
integer
required
task_id
string
required
task_status
string
required
updated_at
integer
required
message
string
required
request_id
string
required
Example
{
"code": 0,
"data": {
"created_at": 1747877033505,
"task_id": "Cjz0o2gmuJkAAAAAAf-32g",
"task_status": "submitted",
"updated_at": 1747877033505
},
"message": "YEScale - Kling Image - Submit: SUCCEED",
"request_id": "Cjz0o2gmuJkAAAAAAf-32g"
}