> ## Documentation Index > Fetch the complete documentation index at: https://docs.kapon.cloud/llms.txt > Use this file to discover all available pages before exploring further. # 图生视频（Legacy） > 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` * 本页对应官方 Legacy 协议；新版请求请使用 [API 2.0](/kling/api2-kling3)。 * 字段详解：请参考[官网权威文档](https://kling.ai/document-api/api/video/3-0-omni/image-to-video/legacy) 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-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 | 条件必填 | 首帧图片 URL 或 Base64；与尾帧至少提供一个，只有支持尾帧独立生成的模型可省略 | | `image_tail` | string | 否 | 尾帧图片 URL 或 Base64 | | `prompt` | string | 否 | 文本提示词 | | `multi_shot` | boolean | 否 | 是否多镜头，默认false，3.0支持 | | `shot_type` | string | 条件必填 | `customize/intelligence` | | `multi_prompt` | array | 条件必填 | 自定义分镜 `{index,prompt,duration}`；最多6段，总时长须一致 | | `element_list` | array | 否 | 3.0主体引用 `[{"element_id":...}]`，最多3个，与voice\_list互斥 | | `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`（按对应模型声音能力使用） | | `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`；3.0额外支持`4k`，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 | 视频时长字符串：3.0支持`3`～`15`，其他模型按其支持范围，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` 与 `image_tail` 至少提供一个；V1.5/V1.6 的 pro 模式支持仅尾帧，其余模型请提供首帧。 > * `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 使用 [新版入口](/kling/api2/image-to-video-3-0-turbo)，不使用旧版别名。 动态笔刷配置 ```json theme={null} { "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 theme={null} curl --request POST \ --url https://models.kapon.cloud/kling/v1/videos/image2video \ --header 'Authorization: Bearer ' \ --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 theme={null} curl --request POST \ --url https://models.kapon.cloud/kling/v1/videos/image2video \ --header 'Authorization: Bearer ' \ --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 theme={null} curl --request POST \ --url https://models.kapon.cloud/kling/v1/videos/image2video \ --header 'Authorization: Bearer ' \ --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 theme={null} { "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 POST /kling/v1/videos/image2video openapi: 3.0.3 info: title: Kling API version: '2026-09-07' description: API 2.0 与 Legacy 分开定义；请求使用 Kapon Token。 servers: - url: https://models.kapon.cloud security: - BearerAuth: [] paths: /kling/v1/videos/image2video: post: tags: - Kling summary: Image to video requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/kling.OfficialImage2VideoRequest' responses: '200': description: OK content: application/json: schema: $ref: '#/components/schemas/kling.OfficialResponse' security: - BearerAuth: [] components: schemas: kling.OfficialImage2VideoRequest: type: object properties: aspect_ratio: description: 画面纵横比：16:9, 9:16, 1:1 type: string callback_url: description: 回调通知地址 type: string camera_control: description: 摄像机运动控制 allOf: - $ref: '#/components/schemas/kling.CameraControl' cfg_scale: description: 生成视频的自由度 [0, 1] type: number duration: description: 视频时长：5, 10 type: string dynamic_masks: description: 动态笔刷配置列表（最多6组） type: array items: $ref: '#/components/schemas/kling.DynamicMask' element_list: type: array items: $ref: '#/components/schemas/kling.OmniElementItem' external_task_id: description: 自定义任务ID type: string image: description: 图片URL，必须 type: string image_tail: description: 尾帧图片 type: string mode: description: 生成模式：std, pro type: string model_name: description: 模型名称，默认kling-v1 type: string multi_prompt: type: array items: $ref: '#/components/schemas/kling.OfficialVideoShot' multi_shot: type: boolean negative_prompt: description: 负向文本提示词 type: string prompt: description: 文本提示词 type: string shot_type: type: string sound: description: 是否生成声音：on/off type: string static_mask: description: 静态笔刷涂抹区域 type: string voice_list: description: 语音列表 type: array items: $ref: '#/components/schemas/kling.VoiceItem' watermark_info: description: 水印信息 allOf: - $ref: '#/components/schemas/kling.OfficialWatermarkInfo' kling.OfficialResponse: type: object properties: code: description: 错误码 type: integer data: description: 单个任务数据 allOf: - $ref: '#/components/schemas/kling.OfficialTaskData' data_list: description: 任务列表数据（用于列表查询） type: array items: $ref: '#/components/schemas/kling.OfficialTaskData' message: description: 错误信息 type: string request_id: description: 请求ID type: string kling.CameraControl: type: object properties: config: description: 当type为"simple"时必填 allOf: - $ref: '#/components/schemas/kling.CameraControlConfig' type: description: >- "simple", "down_back", "forward_up", "right_turn_forward", "left_turn_forward" type: string kling.DynamicMask: type: object properties: mask: description: 动态笔刷涂抹区域 type: string trajectories: description: 运动轨迹坐标序列 type: array items: $ref: '#/components/schemas/kling.TrajectoryPoint' kling.OmniElementItem: type: object properties: element_id: description: 主体ID，保留64位整数精度 type: integer format: int64 kling.OfficialVideoShot: type: object properties: duration: type: string index: type: integer prompt: type: string kling.VoiceItem: type: object properties: voice_id: description: 音色ID type: string kling.OfficialWatermarkInfo: type: object properties: enabled: description: 是否生成含水印结果 type: boolean kling.OfficialTaskData: type: object properties: created_at: description: 任务创建时间，Unix时间戳、单位ms type: integer final_balance_deduction: type: object final_unit_deduction: description: 实际扣减积分 type: string platform_id: description: One-Hub 平台统一追踪 ID（video_） type: string task_id: description: 任务ID — 上游原始任务 ID type: string task_info: description: 任务创建时的参数信息 allOf: - $ref: '#/components/schemas/kling.OfficialTaskInfo' task_result: description: 任务结果 allOf: - $ref: '#/components/schemas/kling.OfficialTaskResult' task_status: description: 任务状态 type: string task_status_msg: description: 任务状态信息 type: string updated_at: description: 任务更新时间，Unix时间戳、单位ms type: integer watermark_info: description: 水印信息 allOf: - $ref: '#/components/schemas/kling.OfficialWatermarkInfo' kling.CameraControlConfig: type: object properties: horizontal: description: 水平运镜 [-10, 10] type: number pan: description: 水平摇镜 [-10, 10] type: number roll: description: 旋转运镜 [-10, 10] type: number tilt: description: 垂直摇镜 [-10, 10] type: number vertical: description: 垂直运镜 [-10, 10] type: number zoom: description: 变焦 [-10, 10] type: number kling.TrajectoryPoint: type: object properties: x: description: 轨迹点横坐标（以输入图片左下为原点的像素坐标） type: integer 'y': description: 轨迹点纵坐标（以输入图片左下为原点的像素坐标） type: integer kling.OfficialTaskInfo: type: object properties: external_task_id: description: 客户自定义任务ID type: string kling.OfficialTaskResult: type: object properties: videos: type: array items: $ref: '#/components/schemas/kling.OfficialVideoResult' kling.OfficialVideoResult: type: object properties: duration: description: 视频总时长，单位s type: string id: description: 生成的视频ID type: string url: description: 生成视频的URL type: string watermark_url: description: 含水印视频下载URL type: string securitySchemes: BearerAuth: type: http scheme: bearer ````