Text Models
Image Models
Video Models
- POSTText to Video
- POSTImage to Video
- POSTMulti-Image to Video
- POSTVideo Extension
- POSTTTS
- POSTAvatar
- POSTLip-Sync
- POSTCounterpart Task Creation
- POSTVideo Effects
- POSTText to Audio
- POSTVideo to Audio
- POSTImage Generation
- POSTMulti-Image to Image
- POSTImage Expansion
- POSTImage Recognition
- POSTVirtual Try-On
- GETIndividual Queries
- POSTOmni Video
- GETOmni Query
- Callback URL
Image Generation
Generate images with Kling via CometAPI: POST /kling/v1/images/generations supports prompt-driven creation with fast, programmatic outputs.
curl --request POST \
--url https://api.cometapi.com/kling/v1/images/generations \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"prompt": "cry"
}
'{
"code": 123,
"data": {
"created_at": 123,
"task_id": "<string>",
"task_info": {
"external_task_id": null
},
"task_result": null,
"task_status": "<string>",
"task_status_msg": null,
"updated_at": 123
},
"message": "<string>"
}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.
Image generation
First request
Start with a concise prompt and the minimum required fields shown in the API playground. Add style, aspect ratio, or advanced controls only after the first request returns a usable image.Read the response
Save the returned task or image fields before starting downstream work. If your workflow needs durable storage, copy the final asset into your own storage layer after generation completes.Authorizations
Bearer token authentication. Use your CometAPI key.
Headers
Must be application/json.
Body
Text prompt describing the image to generate. Maximum 500 characters.
Elements to exclude from the image. Maximum 200 characters.
Reference image as a Base64 string (without data: prefix) or public URL. Accepted formats: JPG, JPEG, PNG. Maximum 10 MB, minimum 300×300 px.
How closely the output follows the reference image. Range: 0–1.
Number of images to generate. Range: 1–9.
Output aspect ratio (width:height). Options: 16:9, 9:16, 1:1, 4:3, 3:4, 3:2, 2:3.
Webhook URL to receive task status updates when the task completes.
Kling image model variant to use. See the Models page for current options.
curl --request POST \
--url https://api.cometapi.com/kling/v1/images/generations \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"prompt": "cry"
}
'{
"code": 123,
"data": {
"created_at": 123,
"task_id": "<string>",
"task_info": {
"external_task_id": null
},
"task_result": null,
"task_status": "<string>",
"task_status_msg": null,
"updated_at": 123
},
"message": "<string>"
}