创建视频任务

Endpoint

POST /v1/video/generations

Header 参数

Name	Type	Required	Description	Example
Authorization	string	No		Bearer {your_token}

请求体参数

Field	Type	Required	Title	Description
model	string	Yes	模型名称	kling-v3-std-silent, kling-v3-std-audio, kling-v3-pro-silent, kling-v3-pro-audio
prompt	string	Yes	主提示词	图生模式下不能与 extra_body.multi_prompt 同时传
image	string	Yes	参考图URL	传/图生视频, 不传/文生视频（注：若有last_image，则是首帧图）
last_image	string	Yes	结束帧图 URL
aspect_ratio	string	Yes	输出画幅比例	允许值：16:9、9:16、1:1，（注：图生视频模式下不保证有效，以输出视频为准）
duration	string	Yes	视频时长（秒）	允许值：3 到 15
extra_body	object	Yes

请求示例

文生视频

{
  "model": "kling-v3-std-silent",
  "prompt": "广角电影感镜头，一个旅行者独自穿过满是尘土的沙漠废墟，披风被风吹动，镜头缓慢拉远，动作真实自然，氛围感强。",
  "aspect_ratio": "16:9",
  "duration": 5,
  "extra_body": {
    "cfg_scale": 0.5,
    "shot_type": "customize",
    "negative_prompt": "模糊, 低细节"
  }
}

curl -X POST "{BASE_URL}/v1/video/generations" \
  -H "Authorization: Bearer sk-***" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "kling-v3-std-silent",
    "prompt": "广角电影感镜头，一个旅行者独自穿过满是尘土的沙漠废墟，披风被风吹动，镜头缓慢拉远，动作真实自然，氛围感强。",
    "aspect_ratio": "16:9",
    "duration": 5,
    "extra_body": {
        "cfg_scale": 0.5,
        "shot_type": "customize",
        "negative_prompt": "模糊, 低细节"
    }
}'

图生视频

{
  "model": "kling-v3-pro-audio",
  "prompt": "人物自然地在笔记本上书写，手部动作细腻，头部有轻微思考停顿，景深柔和，课堂环境真实。",
  "image": "https://example.com/start-frame.png",
  "aspect_ratio": "16:9",
  "duration": 6,
  "extra_body": {
    "cfg_scale": 0.6,
    "shot_type": "intelligent",
    "negative_prompt": "伪影, 畸变"
  }
}

curl -X POST "{BASE_URL}/v1/video/generations" \
  -H "Authorization: Bearer sk-***" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "kling-v3-pro-audio",
    "prompt": "人物自然地在笔记本上书写，手部动作细腻，头部有轻微思考停顿，景深柔和，课堂环境真实。",
    "image": "https://example.com/start-frame.png",
    "aspect_ratio": "16:9",
    "duration": 6,
    "extra_body": {
        "cfg_scale": 0.6,
        "shot_type": "intelligent",
        "negative_prompt": "伪影, 畸变"
    }
}'

首尾帧图生视频

{
  "model": "kling-v3-pro-silent",
  "prompt": "肖像人物逐渐转向镜头，身份保持稳定，动作自然。",
  "image": "https://example.com/first-frame.png",
  "last_image": "https://example.com/last-frame.png",
  "duration": 8,
  "extra_body": {
    "cfg_scale": 0.5,
    "shot_type": "customize"
  }
}

curl -X POST "{BASE_URL}/v1/video/generations" \
  -H "Authorization: Bearer sk-***" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "kling-v3-pro-silent",
    "prompt": "肖像人物逐渐转向镜头，身份保持稳定，动作自然。",
    "image": "https://example.com/first-frame.png",
    "last_image": "https://example.com/last-frame.png",
    "duration": 8,
    "extra_body": {
        "cfg_scale": 0.5,
        "shot_type": "customize"
    }
}'

使用multi_prompt的图生视频

{
  "model": "kling-v3-std-audio",
  "image": "https://example.com/source-image.png",
  "duration": 10,
  "extra_body": {
    "multi_prompt": [
      {
        "prompt": "镜头先以中近景开始，人物低头。"
      },
      {
        "prompt": "人物抬头并看向镜头。"
      }
    ],
    "shot_type": "customize"
  }
}

curl -X POST "{BASE_URL}/v1/video/generations" \
  -H "Authorization: Bearer sk-***" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "kling-v3-std-audio",
    "image": "https://example.com/source-image.png",
    "duration": 10,
    "extra_body": {
        "multi_prompt": [
            {
                "prompt": "镜头先以中近景开始，人物低头。"
            },
            {
                "prompt": "人物抬头并看向镜头。"
            }
        ],
        "shot_type": "customize"
    }
}'

响应字段

Field	Type	Required	Title	Description

响应示例

示例 1

{}