> ## 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.
# Tạo ảnh Kling từ nhiều ảnh
> Sử dụng endpoint Kling Multi-Image to Image của CometAPI để tạo một ảnh mới từ các ảnh tham chiếu về chủ thể, cảnh và phong cách.
Sử dụng endpoint này khi bạn muốn Kling tạo một ảnh từ nhiều ảnh tham chiếu chủ thể cùng với các ảnh tham chiếu cảnh hoặc phong cách tùy chọn.
## Trước khi gọi
* Cung cấp từ 1 đến 4 ảnh trong `subject_image_list`
* Sử dụng `model_name: kling-v2-1` cho các request mới
* Chỉ thêm `scene_image` hoặc `style_image` khi bố cục chủ thể cốt lõi đã hoạt động đúng
* Xem đây là một tuyến tạo ảnh async và lưu task id được trả về
## Luồng tác vụ
Gửi danh sách ảnh chủ thể và prompt, sau đó lưu task id được trả về.
Thăm dò tác vụ được trả về bằng đường dẫn truy vấn ảnh Kling tương ứng cho đến khi tác vụ đạt trạng thái kết thúc.
Lưu ảnh được tạo vào hệ thống lưu trữ của riêng bạn nếu bạn cần truy cập lâu dài.
Để xem tài liệu tham khảo đầy đủ về tham số, hãy xem [tài liệu Kling chính thức](https://kling.ai/document-api/api/image/2-1/multi-image-to-image).
## OpenAPI
````yaml api/openapi/image/kling/post-multi-image-to-image.openapi.json POST /kling/v1/images/multi-image2image
openapi: 3.1.0
info:
title: Kling Multi-Image to Image API
version: 1.0.0
servers:
- url: https://api.cometapi.com
security:
- bearerAuth: []
paths:
/kling/v1/images/multi-image2image:
post:
summary: Generate a Kling image from multiple images
operationId: kling_multi_image_to_image
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:
- subject_image_list
properties:
model_name:
type: string
description: >-
Model to use for multi-image generation. Use `kling-v2-1`
for new requests; omitting the field uses the legacy route
default.
enum:
- kling-v2
- kling-v2-1
default: kling-v2
prompt:
type: string
description: >-
Text prompt describing the desired output. Maximum 2500
characters.
negative_prompt:
type: string
description: Elements to exclude from the image. Maximum 2500 characters.
subject_image_list:
type: array
description: Subject reference images. Minimum 1, maximum 4.
minItems: 1
maxItems: 4
items:
type: object
required:
- subject_image
properties:
subject_image:
type: string
description: >-
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.
scene_image:
type: string
description: >-
Optional scene reference image. 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.
style_image:
type: string
description: >-
Optional style reference image. 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.
'n':
type: integer
description: 'Number of images to generate. Range: 1-9.'
minimum: 1
maximum: 9
default: 1
aspect_ratio:
type: string
description: Aspect ratio of the generated image.
enum:
- '16:9'
- '9:16'
- '1:1'
- '4:3'
- '3:4'
- '3:2'
- '2:3'
- '21:9'
default: '16:9'
watermark_info:
type: object
description: Watermark options.
properties:
enabled:
type: boolean
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: kling-v2-1
prompt: Two product mascots standing together in a bright studio scene
subject_image_list:
- subject_image: https://your-image-host/subject-1.png
- subject_image: https://your-image-host/subject-2.png
scene_image: https://your-image-host/scene.png
style_image: https://your-image-host/style.png
'n': 1
aspect_ratio: '1:1'
examples:
Default:
summary: Multi-image reference request
value:
model_name: kling-v2-1
prompt: >-
Two product mascots standing together in a bright studio
scene
subject_image_list:
- subject_image: https://your-image-host/subject-1.png
- subject_image: https://your-image-host/subject-2.png
scene_image: https://your-image-host/scene.png
style_image: https://your-image-host/style.png
'n': 1
aspect_ratio: '1:1'
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/multi-image2image \
-H "Authorization: Bearer $COMETAPI_KEY" \
-H "Content-Type: application/json" \
-d '{
"model_name": "kling-v2-1",
"prompt": "Two product mascots standing together in a bright studio scene",
"subject_image_list": [
{
"subject_image": "https://your-image-host/subject-1.png"
},
{
"subject_image": "https://your-image-host/subject-2.png"
}
],
"scene_image": "https://your-image-host/scene.png",
"style_image": "https://your-image-host/style.png",
"n": 1,
"aspect_ratio": "1:1"
}'
- lang: Python
label: Default
source: |
import os
import requests
response = requests.post(
"https://api.cometapi.com/kling/v1/images/multi-image2image",
headers={"Authorization": "Bearer " + os.environ["COMETAPI_KEY"]},
json={
"model_name": "kling-v2-1",
"prompt": "Two product mascots standing together in a bright studio scene",
"subject_image_list": [
{
"subject_image": "https://your-image-host/subject-1.png"
},
{
"subject_image": "https://your-image-host/subject-2.png"
}
],
"scene_image": "https://your-image-host/scene.png",
"style_image": "https://your-image-host/style.png",
"n": 1,
"aspect_ratio": "1:1"
},
)
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/multi-image2image",
{
method: "POST",
headers: {
Authorization: `Bearer ${process.env.COMETAPI_KEY}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"model_name": "kling-v2-1",
"prompt": "Two product mascots standing together in a bright studio scene",
"subject_image_list": [
{
"subject_image": "https://your-image-host/subject-1.png"
},
{
"subject_image": "https://your-image-host/subject-2.png"
}
],
"scene_image": "https://your-image-host/scene.png",
"style_image": "https://your-image-host/style.png",
"n": 1,
"aspect_ratio": "1:1"
}),
});
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.
````