curl --request POST \
--url https://api.evolink.ai/v1/videos/generations \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"model": "kling-o3-image-to-video",
"prompt": "让画面中的人物缓缓转头微笑",
"image_start": "https://example.com/portrait.jpg",
"duration": 5,
"quality": "720p"
}
'
{
"created": 1757169743,
"id": "task-unified-1757169743-7cvnl5zw",
"model": "kling-o3-image-to-video",
"object": "video.generation.task",
"progress": 0,
"status": "pending",
"task_info": {
"can_cancel": true,
"estimated_time": 300,
"video_duration": 9
},
"type": "video",
"usage": {
"billing_rule": "per_call",
"credits_reserved": 7,
"user_group": "default"
}
}{
"error": {
"code": "invalid_request",
"message": "Invalid request parameters",
"type": "invalid_request_error"
}
}{
"error": {
"code": "unauthorized",
"message": "Invalid or expired token",
"type": "authentication_error"
}
}{
"error": {
"code": "insufficient_quota",
"message": "Insufficient quota. Please top up your account.",
"type": "insufficient_quota"
}
}{
"error": {
"code": "model_access_denied",
"message": "Token does not have access to model: kling-o3-image-to-video",
"type": "invalid_request_error"
}
}{
"error": {
"code": "rate_limit_exceeded",
"message": "Too many requests, please try again later",
"type": "rate_limit_error"
}
}{
"error": {
"code": "internal_error",
"message": "Internal server error",
"type": "api_error"
}
}Kling-O3
Kling-O3 图生视频
- Kling-O3 Image to Video (kling-o3-image-to-video) 基于输入图片生成视频,基于可灵 AI kling-v3-omni 模型
- 支持首帧、尾帧、参考图、主体控制、多镜头、音效
- 异步处理模式,使用返回的任务ID 进行查询
- 生成的视频链接,有效期为24小时,请尽快保存
POST
/
v1
/
videos
/
generations
curl --request POST \
--url https://api.evolink.ai/v1/videos/generations \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"model": "kling-o3-image-to-video",
"prompt": "让画面中的人物缓缓转头微笑",
"image_start": "https://example.com/portrait.jpg",
"duration": 5,
"quality": "720p"
}
'
{
"created": 1757169743,
"id": "task-unified-1757169743-7cvnl5zw",
"model": "kling-o3-image-to-video",
"object": "video.generation.task",
"progress": 0,
"status": "pending",
"task_info": {
"can_cancel": true,
"estimated_time": 300,
"video_duration": 9
},
"type": "video",
"usage": {
"billing_rule": "per_call",
"credits_reserved": 7,
"user_group": "default"
}
}{
"error": {
"code": "invalid_request",
"message": "Invalid request parameters",
"type": "invalid_request_error"
}
}{
"error": {
"code": "unauthorized",
"message": "Invalid or expired token",
"type": "authentication_error"
}
}{
"error": {
"code": "insufficient_quota",
"message": "Insufficient quota. Please top up your account.",
"type": "insufficient_quota"
}
}{
"error": {
"code": "model_access_denied",
"message": "Token does not have access to model: kling-o3-image-to-video",
"type": "invalid_request_error"
}
}{
"error": {
"code": "rate_limit_exceeded",
"message": "Too many requests, please try again later",
"type": "rate_limit_error"
}
}{
"error": {
"code": "internal_error",
"message": "Internal server error",
"type": "api_error"
}
}授权
##所有接口均需要使用Bearer Token进行认证##
获取 API Key:
访问 API Key 管理页面 获取您的 API Key
使用时在请求头中添加:
Authorization: Bearer YOUR_API_KEY
请求体
application/json
视频生成模型名称
可用选项:
kling-o3-image-to-video 示例:
"kling-o3-image-to-video"
文本提示词。multi_shot=false(默认)时必填,multi_shot=true 时由 multi_prompt 提供各分镜内容
说明:
- 最长
2500字符 - 可通过
<<<element_1>>>引用主体,<<<image_1>>>引用参考图
Maximum string length:
2500首帧图片 URL
图片格式要求:
- 格式:JPG / JPEG / PNG
- 大小:≤ 10MB
- 尺寸:宽高 ≥ 300px,宽高比在 1:2.5 ~ 2.5:1 之间
- 图像URL需要服务器能直接访问,或者访问时会直接下载
尾帧图片 URL
约束:
- 有尾帧必须有首帧
- 总图片数超过 2 时不支持尾帧
- 图像URL需要服务器能直接访问,或者访问时会直接下载
参考图 URL 数组(非首帧/尾帧,用于风格/场景/主体参考)
说明:
- 图像URL需要服务器能直接访问,或者访问时会直接下载
视频时长(秒),范围 3~15 的整数
必填范围:
3 <= x <= 15画面宽高比
可用选项:
16:9, 9:16, 1:1 分辨率档位
说明:
720p:标清1080p:高清4k:超高清
可用选项:
720p, 1080p, 4k 音效控制
可用选项:
on, off 模型扩展参数
Show child attributes
Show child attributes
任务完成后的HTTPS回调地址
回调时机:
- 任务完成(completed)、失败(failed)或取消(cancelled)时触发
- 在计费确认完成后发送
安全限制:
- 仅支持HTTPS协议
- 禁止回调到内网IP地址(127.0.0.1、10.x.x.x、172.16-31.x.x、192.168.x.x等)
- URL长度不超过
2048字符
回调机制:
- 超时时间:
10秒 - 失败后最多重试
3次(会分别在失败的1秒/2秒/4秒后进行重试) - 回调响应体格式与任务查询接口返回的格式一致
- 回调地址若返回2xx状态码视为成功,其他状态码会触发重试
示例:
"https://your-domain.com/webhooks/video-task-completed"
响应
视频生成任务创建成功
任务创建时间戳
示例:
1757169743
任务ID
示例:
"task-unified-1757169743-7cvnl5zw"
实际使用的模型名称
示例:
"kling-o3-image-to-video"
任务的具体类型
可用选项:
video.generation.task 任务进度百分比 (0-100)
必填范围:
0 <= x <= 100示例:
0
任务状态
可用选项:
pending, processing, completed, failed 示例:
"pending"
视频任务详细信息
Show child attributes
Show child attributes
任务的输出类型
可用选项:
text, image, audio, video 示例:
"video"
使用量和计费信息
Show child attributes
Show child attributes