> ## Documentation Index > Fetch the complete documentation index at: https://evolink.ai/docs/llms.txt > Use this file to discover all available pages before exploring further. # Tencent 视频超分辨率 > - Tencent Video Upscale (tencent-video-upscale) 对已有视频做画质增强，并放大到目标清晰度：`720p`、`1080p`、`2k` 或 `4k` - 提供 7 种增强风格，覆盖真人实拍、动画、远景小人脸、人脸保真、细节强化和柔和效果 - 帧率默认沿用原视频（`model_params.max_fps: "source"`）；可设 `"30"`、`"60"`、`"120"` 作为上限，只降不升，不会补帧 - 按视频时长计费，不同清晰度和输出帧率的价格请以 [EvoLink 模型价格](https://evolink.ai/models) 为准 - 异步处理模式，使用返回的任务ID [进行查询](/cn/api-manual/task-management/get-task-detail) - 任务提交后不可取消 - 增强后的视频链接有效期为24小时，请尽快保存 ## OpenAPI ````yaml cn/api-manual/video-series/tencent/tencent-video-upscale.json POST /v1/videos/generations openapi: 3.1.0 info: title: tencent-video-upscale 接口 description: 使用 Tencent Video Upscale 进行视频画质增强，并放大到 720p、1080p、2K 或 4K license: name: MIT version: 1.0.0 servers: - url: https://api.evolink.ai description: 生产环境 security: - bearerAuth: [] tags: - name: 视频生成 description: AI视频生成相关接口 paths: /v1/videos/generations: post: tags: - 视频生成 summary: tencent-video-upscale 接口 description: >- - Tencent Video Upscale (tencent-video-upscale) 对已有视频做画质增强，并放大到目标清晰度：`720p`、`1080p`、`2k` 或 `4k` - 提供 7 种增强风格，覆盖真人实拍、动画、远景小人脸、人脸保真、细节强化和柔和效果 - 帧率默认沿用原视频（`model_params.max_fps: "source"`）；可设 `"30"`、`"60"`、`"120"` 作为上限，只降不升，不会补帧 - 按视频时长计费，不同清晰度和输出帧率的价格请以 [EvoLink 模型价格](https://evolink.ai/models) 为准 - 异步处理模式，使用返回的任务ID [进行查询](/cn/api-manual/task-management/get-task-detail) - 任务提交后不可取消 - 增强后的视频链接有效期为24小时，请尽快保存 operationId: createTencentVideoUpscaleTask requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/VideoGenerationRequest' examples: default_1080p: summary: 默认（通用真实风格、1080p、沿用原视频帧率） value: model: tencent-video-upscale video_urls: - https://example.com/my-video.mp4 explicit_defaults: summary: 与上例等价：把默认值全部写出 value: model: tencent-video-upscale video_urls: - https://example.com/my-video.mp4 mode: realistic quality: 1080p model_params: max_fps: source animation_4k: summary: 动画视频增强到 4K value: model: tencent-video-upscale video_urls: - https://example.com/my-animation.mp4 mode: animation quality: 4k cap_frame_rate: summary: 高帧率视频限制在 30 帧 value: model: tencent-video-upscale video_urls: - https://example.com/my-60fps-video.mp4 quality: 1080p model_params: max_fps: '30' with_callback: summary: 带回调URL value: model: tencent-video-upscale video_urls: - https://example.com/my-video.mp4 mode: face_fidelity quality: 2k callback_url: https://your-domain.com/webhooks/video-task-completed responses: '200': description: 视频增强任务创建成功 content: application/json: schema: $ref: '#/components/schemas/VideoGenerationResponse' '400': description: 请求参数错误 content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' examples: missing_video: summary: 缺少视频URL value: error: code: invalid_parameter message: >- video_urls is required and must not be empty for tencent-video-upscale type: invalid_request_error invalid_mode: summary: 风格取值无效 value: error: code: invalid_parameter message: >- invalid mode "general" for tencent-video-upscale; supported: realistic, realistic_distant, animation, animation_distant, face_fidelity, detail_boost, soft type: invalid_request_error invalid_max_fps: summary: 帧率上限取值无效 value: error: code: invalid_parameter message: >- invalid model_params.max_fps auto for tencent-video-upscale; supported: "source", 30, 60, 120 type: invalid_request_error too_long: summary: 视频超过 60 秒 value: error: code: invalid_parameter message: video duration 75.2s exceeds the 60s limit type: invalid_request_error source_too_large: summary: 原视频超过 4K value: error: code: invalid_parameter message: >- source video resolution exceeds 4K (short side 2880px > 2160px) type: invalid_request_error target_too_low: summary: 目标清晰度低于原视频 value: error: code: invalid_parameter message: >- target quality 720p is lower than the source video (short side 1080px); choose a higher quality type: invalid_request_error top_level_fps: summary: 不支持顶层 fps 参数 value: error: code: invalid_parameter message: >- fps is not supported for tencent-video-upscale; use model_params.max_fps (30, 60 or 120) to cap the output frame rate type: invalid_request_error probe_failed: summary: 读取视频信息失败 value: error: code: video_probe_failed message: >- Failed to read the video's duration, resolution and frame rate. Please provide a publicly downloadable MP4 or MOV video URL type: invalid_request_error '401': description: 未认证、Token无效或过期 content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' example: error: code: unauthorized message: Invalid or expired token type: authentication_error '402': description: 配额不足、需要充值 content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' example: error: code: insufficient_quota message: Insufficient quota. Please top up your account. type: insufficient_quota '403': description: 无权限访问 content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' example: error: code: model_access_denied message: 'Token does not have access to model: tencent-video-upscale' type: invalid_request_error '429': description: 请求频率超限 content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' example: error: code: rate_limit_exceeded message: Too many requests, please try again later type: rate_limit_error '500': description: 服务器内部错误 content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' example: error: code: internal_error message: Internal server error type: api_error '503': description: 服务暂时不可用，请稍后重试或联系客服 content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' components: schemas: VideoGenerationRequest: type: object required: - model - video_urls properties: model: type: string description: 视频超分模型名称 enum: - tencent-video-upscale default: tencent-video-upscale example: tencent-video-upscale video_urls: type: array description: |- 输入视频URL列表 **注意：** - 每次请求仅支持 `1` 个视频（多传只取第一个） - 视频URL必须可被服务器直接访问（公共URL或预签名URL） - 支持的格式：`.mp4`、`.mov` - 最长时长：`60` 秒 - 原视频清晰度最高 4K（短边不超过 `2160` 像素） - 提交时服务器会先读取视频的时长、分辨率和帧率，读取失败会返回 `video_probe_failed` items: type: string format: uri minItems: 1 maxItems: 1 example: - https://example.com/my-video.mp4 mode: type: string description: |- 增强风格，按视频内容选择 **可选项：** - `realistic` - 通用真实：真人实拍等常规画面 — **默认值** - `realistic_distant` - 真实 · 远景：远景拍摄，针对画面里的小人脸优化 - `animation` - 通用动画：动画、动漫、卡通内容 - `animation_distant` - 动画 · 远景：远景角色较多的动画，针对小人脸优化 - `face_fidelity` - 人脸保真：尽量保留原视频的人脸特征 - `detail_boost` - 细节强化：纹理和边缘细节更明显 - `soft` - 柔和：锐化更轻，观感更自然 不区分大小写，无效值会被拒绝 enum: - realistic - realistic_distant - animation - animation_distant - face_fidelity - detail_boost - soft default: realistic example: realistic quality: type: string description: |- 目标清晰度，按视频短边计算 **可选项：** - `720p` - 短边 `720` 像素 - `1080p` - 短边 `1080` 像素 — **默认值** - `2k` - 短边 `1440` 像素 - `4k` - 短边 `2160` 像素 **注意：** - 目标清晰度不能低于原视频，例如 `1080p` 的原视频可选 `1080p`、`2k`、`4k`，选 `720p` 会被拒绝 - 选择不低于原视频的最低一档，画面基本不放大 enum: - 720p - 1080p - 2k - 4k default: 1080p example: 1080p model_params: type: object description: 模型特定参数 properties: max_fps: type: string description: |- 输出视频的帧率上限。默认 `"source"`，即沿用原视频帧率；不传与 `"source"` 等价 **可选项：** - `"source"` - 沿用原视频帧率 — **默认值** - `"30"` - 输出帧率不超过 30 帧/秒 - `"60"` - 输出帧率不超过 60 帧/秒 - `"120"` - 输出帧率不超过 120 帧/秒 **行为说明：** - 原视频帧率不超过上限时保持原帧率，**不会补帧**；超过上限时降到上限 - 使用 `"source"` 或不传时，原视频超过 `120` 帧/秒仍会降到 `120` 帧/秒 **类型说明：** - 推荐使用字符串，也兼容整数 `30`、`60`、`120`（例如 `"60"` 和 `60` 等价） - `"source"` 不区分大小写 - 其他取值（如 `45`、`60.5`、`"auto"`）会被拒绝 - 本模型不接受顶层 `fps` 参数 enum: - source - '30' - '60' - '120' default: source example: '30' callback_url: type: string description: |- 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 format: uri example: https://your-domain.com/webhooks/video-task-completed VideoGenerationResponse: type: object properties: created: type: integer description: 任务创建时间戳 example: 1757169743 id: type: string description: 任务ID example: task-unified-1757169743-7cvnl5zw model: type: string description: 实际使用的模型名称 example: tencent-video-upscale object: type: string enum: - video.generation.task description: 任务的具体类型 progress: type: integer description: 任务进度百分比 (0-100) minimum: 0 maximum: 100 example: 0 status: type: string description: 任务状态 enum: - pending - processing - completed - failed example: pending task_info: $ref: '#/components/schemas/VideoTaskInfo' description: 视频任务详细信息 type: type: string enum: - text - image - audio - video description: 任务的输出类型 example: video usage: $ref: '#/components/schemas/VideoUsage' description: 使用量和计费信息 ErrorResponse: type: object properties: error: type: object properties: code: type: string description: 错误代码标识符 message: type: string description: 错误描述信息 type: type: string description: 错误类型 VideoTaskInfo: type: object properties: can_cancel: type: boolean description: 任务是否可以取消（本模型任务提交后不可取消） example: false estimated_time: type: integer description: 预估完成时间（秒），实际耗时受排队情况影响，4K、高帧率和长视频会明显更久 minimum: 0 example: 120 video_duration: type: integer description: 视频时长（秒） example: 0 VideoUsage: type: object description: 使用量和计费信息 properties: billing_rule: type: string description: >- 计费规则。本模型按视频时长（每秒）进行 `per_second` 计费，实际费用请以 [EvoLink 模型价格](https://evolink.ai/models) 为准 enum: - per_call - per_token - per_second example: per_second credits_reserved: type: number description: 预估消耗积分（预授权）。最终消耗积分在任务完成后结算，以账单为准 minimum: 0 example: 3.264 user_group: type: string description: 用户组类别 example: default securitySchemes: bearerAuth: type: http scheme: bearer description: |- ##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](https://evolink.ai/dashboard/keys) 获取您的 API Key **使用时在请求头中添加：** ``` Authorization: Bearer YOUR_API_KEY ``` ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.