> ## Documentation Index > Fetch the complete documentation index at: https://docs.vidgo.ai/llms.txt > Use this file to discover all available pages before exploring further. # Kling 2.5 Turbo Pro 图生视频 > 使用 Kling 2.5 Turbo Pro，以首帧、尾帧或两者加上文本提示词生成视频。 > [!TIP] > > 1. 提交后会返回 `task_id`。如果提供了 `callback_url`，当任务状态变为 `finished` 或 `failed` 时，系统会向 `callback_url` 发送 POST 请求。 > 2. 无论是否提供 `callback_url`，都可以通过统一的[查询任务状态](https://docs.vidgo.ai/zh/api-manual/task-management/status.md)接口获取结果。 使用 Kling 2.5 Turbo Pro，以首帧、尾帧或两者加上文本提示词生成视频。 ## 模型 * **kwaivgi/kling-v2.5-turbo-pro/image-to-video** - 根据图像输入生成视频。 ## 功能 * 根据图像输入生成视频。 * 用 `start_image_url`、`end_image_url` 或两者引导生成。 ## 时长选项 * **5、10 秒** - `duration` 设为整数。可选。默认值：**5 秒**。字符串、布尔值、小数时长和 `null` 会被拒绝。 ## 高级参数 `model` 和可选的 `callback_url` 放在请求根级。所有工作流程参数（包括输出选项）都放在 `input` 中。 只发送该工作流程支持的 input 字段。不支持的 `input` 字段会在扣除积分前被拒绝。输入 URL 必须使用 HTTP(S)、包含主机名，且不含内嵌凭据或空白字符。图像字段不接受数组或 Base64。 ### 提示词 * `prompt`：必填。描述场景和期望的动作。长度：**1-2,500 个字符**。 * 请提供字符串，不能是数字、布尔值、数组或对象。检查 2,500 个 Unicode 字符上限之前会先去除首尾空白。 ### 首帧图像 URL * `start_image_url`：首帧的公开 HTTP(S) URL。仅在省略 `end_image_url` 时必填。 ### 尾帧图像 URL * `end_image_url`：尾帧的公开 HTTP(S) URL。仅在省略 `start_image_url` 时必填。 * 至少提供一帧：仅首帧、仅尾帧或两者都提供。不使用的 URL 字段请省略；空字符串和 `null` 会被拒绝。 ### 宽高比 * `aspect_ratio`：可选字符串。未规定预设选项或默认值。不使用时省略。 ### 负面提示词 * `negative_prompt`：可选。描述需要避免的内容。 ## 计费因素 计费取决于视频时长（`duration`）。文生视频和图生视频费率相同。 提交时扣除积分，任务失败时退还。 ## OpenAPI ````yaml zh/api-manual/video-series/kwaivgi-kling-v2-5-turbo-pro-image-to-video.json POST /api/generate/submit openapi: 3.0.0 info: title: Vidgo API - Kling 2.5 Turbo Pro 图生视频 description: 使用首帧、尾帧或两者，加上文本提示词生成视频。 version: 1.0.0 servers: - url: https://api.vidgo.ai security: - BearerAuth: [] paths: /api/generate/submit: post: tags: - Video Series summary: Kling 2.5 Turbo Pro 图生视频 description: >- 生成参数放在 input 中。不支持的 input 字段和类型错误会在扣除积分前被拒绝。计费取决于视频时长（`duration`）。文生视频和图生视频费率相同。 operationId: submit_kwaivgi_kling_v2_5_turbo_pro_image_to_video requestBody: required: true content: application/json: schema: type: object required: - model - input additionalProperties: true properties: model: type: string example: kwaivgi/kling-v2.5-turbo-pro/image-to-video input: type: object required: - prompt properties: prompt: type: string description: 必填的非空字符串，去除首尾空白后最多 2,500 个 Unicode 字符。 maxLength: 2500 example: >- A man in a trench coat holding a black umbrella walks briskly through the streets of Tokyo on a rainy night, splashing through puddles. A handheld follow-cam shot from his side and slightly behind. The focus is locked on the man, while background neon signs blur into beautiful bokeh. Cyberpunk aesthetic with a film noir quality; the mood is mysterious and lonely. The pavement is slick and wet, reflecting the vibrant neon signs. Individual raindrops are visible, and a light fog hangs in the air. minLength: 1 duration: type: integer description: 整数 5 或 10 秒；省略时默认为 5。字符串、布尔值、小数时长和 null 会被拒绝。 enum: - 5 - 10 default: 5 example: 5 start_image_url: type: string format: uri description: >- 首帧的公开 HTTP(S) URL，不含凭据或空白字符。提供 start_image_url、end_image_url 或两者都提供。不使用时省略；空字符串和 null 会被拒绝。 example: >- https://cdn.doculator.org/kling-2.5-turbo-pro/start-image.jpeg end_image_url: type: string format: uri description: >- 尾帧的公开 HTTP(S) URL，不含凭据或空白字符。提供 start_image_url、end_image_url 或两者都提供。不使用时省略；空字符串和 null 会被拒绝。 example: https://example.com/end-image.png aspect_ratio: type: string description: 可选的宽高比字符串；没有文档化的枚举值或默认值。不使用时省略。 example: '16:9' negative_prompt: type: string description: 可选字符串，描述需要避免的内容。不使用时省略。 example: low quality, blur additionalProperties: false description: '`start_image_url`、`end_image_url` 至少提供一个。' callback_url: type: string nullable: true description: >- 可选的公开 HTTP(S) 接口，用于接收任务完成通知。建议使用 HTTPS。省略、传 null 或空字符串即可禁用回调。 description: model 和 callback_url 放在根级。未知的根级字段会被忽略；不支持的 input 字段会被拒绝。 examples: basic: summary: 首帧 value: model: kwaivgi/kling-v2.5-turbo-pro/image-to-video input: prompt: A slow camera pan across a sunlit garden. duration: 5 start_image_url: https://example.com/start-frame.png end-frame: summary: 仅尾帧 value: model: kwaivgi/kling-v2.5-turbo-pro/image-to-video input: prompt: A slow camera pan across a sunlit garden. duration: 5 end_image_url: https://example.com/end-frame.png first-last-frame: summary: 首尾帧 value: model: kwaivgi/kling-v2.5-turbo-pro/image-to-video input: prompt: A slow camera pan across a sunlit garden. duration: 5 start_image_url: https://example.com/start-frame.png end_image_url: https://example.com/end-frame.png responses: '200': description: 任务已提交 content: application/json: schema: type: object required: - code - data properties: code: type: integer enum: - 200 data: type: object required: - task_id - status - created_time properties: task_id: type: string status: type: string enum: - not_started - running - finished - failed created_time: type: string format: date-time example: code: 200 data: task_id: task-unified-example status: running created_time: '2026-09-10T08:00:00' '400': description: 输入无效、档位不受支持、媒体无法访问或积分不足 content: application/json: schema: type: object required: - detail properties: detail: oneOf: - type: string - type: object additionalProperties: true - type: array items: {} '401': description: 凭据无效 content: application/json: schema: type: object required: - detail properties: detail: oneOf: - type: string - type: object additionalProperties: true - type: array items: {} '403': description: 拒绝访问 content: application/json: schema: type: object required: - detail properties: detail: oneOf: - type: string - type: object additionalProperties: true - type: array items: {} '404': description: 模型未知或已停用 content: application/json: schema: type: object required: - detail properties: detail: oneOf: - type: string - type: object additionalProperties: true - type: array items: {} '408': description: 请求超时 content: text/plain: schema: type: string example: Request timeout '422': description: JSON 无效或请求体不是对象 content: application/json: schema: type: object required: - detail properties: detail: oneOf: - type: string - type: object additionalProperties: true - type: array items: {} '429': description: 超出请求频率或 API Key 积分限额 content: application/json: schema: type: object required: - detail properties: detail: oneOf: - type: string - type: object additionalProperties: true - type: array items: {} '500': description: 内部错误 content: application/json: schema: type: object required: - detail properties: detail: oneOf: - type: string - type: object additionalProperties: true - type: array items: {} '502': description: 无法创建上游生成任务 content: application/json: schema: type: object required: - detail properties: detail: oneOf: - type: string - type: object additionalProperties: true - type: array items: {} '503': description: 所请求的模型暂时不可用 content: application/json: schema: type: object required: - detail properties: detail: oneOf: - type: string - type: object additionalProperties: true - type: array items: {} components: securitySchemes: BearerAuth: type: http scheme: bearer description: 使用 VIDGO_API_KEY。 ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.