Appearance
图生视频
接口与可灵官网一致;支持首帧驱动、动态笔刷、运镜控制
- 路径
POST /kling/v1/videos/image2video - 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-video-o1、kling-v1、kling-v1-5、kling-v1-6、kling-v2-master、kling-v2-1、kling-v2-1-master、kling-v2-5-turbo、kling-v2-6、kling-v3 |
image | string | 是 | 首帧图片 URL 或 Base64 |
image_tail | string | 否 | 尾帧图片 URL 或 Base64 |
prompt | string | 否 | 文本提示词 |
negative_prompt | string | 否 | 负向文本提示词 |
voice_list | array | 否 | 语音列表(仅 kling-v2-6 支持,最多2个) |
sound | string | 否 | 是否生成声音:on/off(仅 kling-v2-6 支持) |
cfg_scale | number | 否 | 生成自由度 [0, 1],仅 kling-v1/kling-v1-5/kling-v1-6 支持 |
mode | string | 否 | 生成模式:std、pro,默认 std |
static_mask | string | 否 | 静态笔刷涂抹区域 |
dynamic_masks | array | 否 | 动态笔刷配置列表(最多6组) |
camera_control | object | 否 | 摄像机运动控制 |
aspect_ratio | string | 否 | 画面纵横比:16:9、9:16、1:1,默认 16:9 |
duration | string | 否 | 视频时长:5、10,默认 5 |
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 |
重要约束
image必填,image_tail可选;image + image_tail、dynamic_masks/static_mask、camera_control三组选一,互斥不可同时使用;voice_list仅kling-v2-6支持,且使用时sound=on、最多 2 个。kling-v3-omni请使用 Omni 视频入口/kling/v1/videos/omni-video。- 历史输入
kling-v2-5会归一为kling-v2-5-turbo;Kling 3.0 Turbo暂未确认官方可调用 schema,当前不放行。
动态笔刷配置
json
{
"dynamic_masks": [
{
"mask": "base64编码的掩码图片",
"trajectories": [
{"x": 100, "y": 200},
{"x": 150, "y": 250}
]
}
]
}trajectories:运动轨迹坐标序列,以输入图片左下为原点的像素坐标,至少2个点,最多77个点dynamic_masks最多 6 组;static_mask与dynamic_masks.mask分辨率需与image一致,否则上游可能失败
场景一:首帧驱动
bash
curl --request POST \
--url https://aiapi.fhddos.com/kling/v1/videos/image2video \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '{
"model_name": "kling-v1",
"image": "https://example.com/first-frame.jpg",
"prompt": "A mouse runs toward the camera, smiling and blinking",
"mode": "std",
"duration": "5",
"aspect_ratio": "16:9"
}'场景二:首帧 + 尾帧
bash
curl --request POST \
--url https://aiapi.fhddos.com/kling/v1/videos/image2video \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '{
"model_name": "kling-v1",
"image": "https://example.com/child.jpg",
"image_tail": "https://example.com/adult.jpg",
"prompt": "A little girl grows up",
"mode": "pro",
"duration": "10",
"aspect_ratio": "16:9"
}'场景三:使用摄像机运镜
bash
curl --request POST \
--url https://aiapi.fhddos.com/kling/v1/videos/image2video \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '{
"model_name": "kling-v2-master",
"image": "https://example.com/landscape.jpg",
"prompt": "Camera slowly zooms in on the mountain peak",
"camera_control": {
"type": "simple",
"config": {
"zoom": 5
}
},
"duration": "10",
"aspect_ratio": "16:9"
}'示例响应
json
{
"code": 0,
"message": "success",
"request_id": "req_1735558800_xyz789",
"data": {
"task_id": "task_01JGHM...",
"task_status": "submitted",
"created_at": 1735558800000,
"updated_at": 1735558800000
}
}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/videos/image2video:
post:
tags:
- Kling
summary: Kling image to video
requestBody:
$ref: '#/components/requestBodies/MultipartObject'
responses:
'200':
$ref: '#/components/responses/JsonObject'
components:
requestBodies:
MultipartObject:
required: true
content:
multipart/form-data:
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>'