Appearance
图像生成
接口与可灵官网一致;支持文生图、图生图、角色/人脸参考
- 路径
POST /kling/v1/images/generations - 与官网一致:本页所有请求体、字段命名与返回结构与可灵官网保持一致
- 字段详解:请参考官网权威文档
请求参数
| 参数 | 类型 | 必填 | 说明 |
|---|---|---|---|
model_name | string | 否 | 模型名称,默认 kling-v1。可选:kling-image-o1、kling-v1、kling-v1-5、kling-v2、kling-v2-new、kling-v2-1、kling-v3 |
prompt | string | 是 | 正向文本提示词 |
negative_prompt | string | 否 | 负向文本提示词(图生图场景不支持) |
image | string | 否 | 参考图像 URL 或 Base64 |
image_reference | string | 否 | 图片参考类型:subject(角色特征)、face(人物长相),仅 kling-v1-5 支持 |
image_fidelity | number | 否 | 图片参考强度 [0, 1] |
human_fidelity | number | 否 | 面部参考强度 [0, 1] |
resolution | string | 否 | 清晰度:1k(标清)、2k(高清),默认 1k |
n | int | 否 | 生成图片数量 [1, 9],默认 1 |
aspect_ratio | string | 否 | 纵横比:16:9、9:16、1:1、4:3、3:4、3:2、2:3、21:9,默认 16:9 |
watermark_info | object | 否 | 是否生成含水印结果 |
callback_url | string | 否 | 回调通知地址 |
external_task_id | string | 否 | 自定义任务ID |
注意:使用
kling-v1-5且image参数不为空时,image_reference参数必填。非kling-v1-5模型不支持image_reference。补充约束:
prompt长度 ≤ 2500;图生图场景(image非空)不支持negative_prompt。模型边界:
kling-v3-omni仅通过/kling/v1/images/omni-image放行;kling-v2-5-turbo等视频模型不能用于/images/generations。
场景一:文生图
bash
curl --request POST \
--url https://aiapi.fhddos.com/kling/v1/images/generations \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '{
"model_name": "kling-v1",
"prompt": "A beautiful sunset over the ocean, vibrant colors, high detail",
"resolution": "2k",
"n": 1,
"aspect_ratio": "16:9"
}'场景二:角色特征参考
bash
curl --request POST \
--url https://aiapi.fhddos.com/kling/v1/images/generations \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '{
"model_name": "kling-v1-5",
"prompt": "The character holding a magic wand in a fantasy forest",
"image": "https://example.com/character-reference.jpg",
"image_reference": "subject",
"image_fidelity": 0.8,
"resolution": "2k",
"aspect_ratio": "3:4"
}'场景三:人脸参考
bash
curl --request POST \
--url https://aiapi.fhddos.com/kling/v1/images/generations \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '{
"model_name": "kling-v1-5",
"prompt": "A professional headshot portrait, business attire, studio lighting",
"image": "https://example.com/face-photo.jpg",
"image_reference": "face",
"human_fidelity": 0.9,
"resolution": "2k",
"aspect_ratio": "1:1"
}'场景四:批量生成
bash
curl --request POST \
--url https://aiapi.fhddos.com/kling/v1/images/generations \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '{
"model_name": "kling-v2",
"prompt": "Abstract colorful artwork, modern style",
"n": 4,
"resolution": "1k",
"aspect_ratio": "1:1"
}'示例响应
json
{
"code": 0,
"message": "success",
"request_id": "req_1735558800_img123",
"data": {
"task_id": "task_01JGHP...",
"task_status": "submitted",
"created_at": 1735558800000,
"updated_at": 1735558800000
}
}任务成功响应
json
{
"code": 0,
"message": "success",
"data": {
"task_id": "task_01JGHP...",
"task_status": "succeed",
"task_result": {
"images": [
{"index": 0, "url": "https://..."},
{"index": 1, "url": "https://..."}
]
}
}
}OpenAPI
yaml
openapi: 3.0.3
info:
title: Fhddos Core API
version: '1.0'
description: >-
Core OpenAI-compatible and model-family endpoints used by the Fhddos user
docs.
servers:
- url: https://aiapi.fhddos.com
security:
- BearerAuth: []
paths:
/kling/v1/images/generations:
post:
tags:
- Kling
summary: Kling image generation
requestBody:
$ref: '#/components/requestBodies/JsonObject'
responses:
'200':
$ref: '#/components/responses/JsonObject'
components:
requestBodies:
JsonObject:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/GenericObject'
responses:
JsonObject:
description: OK
content:
application/json:
schema:
$ref: '#/components/schemas/GenericObject'
schemas:
GenericObject:
type: object
additionalProperties: true
securitySchemes:
BearerAuth:
type: http
scheme: bearer
description: 'Authorization: Bearer <token>'