> ## Documentation Index > Fetch the complete documentation index at: https://apidoc.cometapi.com/llms.txt > Use this file to discover all available pages before exploring further. # 创建一个 Runway 图生视频任务 > 使用 CometAPI 调用 Runway image_to_video，将静态图片 URL 转换为原始视频输出，并通过 X-Runway-Version 支持兼容性。 使用此端点可将一张源图片制作成带动画效果的 Runway 视频。 ## 调用前准备 * 发送必需的 `X-Runway-Version` 请求头，例如 `2024-11-06` * 使用 `model: gen3a_turbo` * 提供稳定可访问的 HTTPS `promptImage` * 以 `duration: 5` 和所选 Runway model/version 支持的 ratio 值开始 ## Duration 和 ratio | 设置 | 支持的值 | 默认起始值 | 边界行为 | | ------------------------------------------- | --------------------------------------------------------------------------------- | ------------------- | ----------------------------------------------------------- | | `duration` | 取决于 Runway model/version；为获得最广泛兼容性，请使用 `5` 或 `10` | `5` | CometAPI 会将该值转发给 Runway。如果所选 model/version 拒绝该值，请重试并使用 `5`。 | | 带有 `X-Runway-Version: 2024-11-06` 的 `ratio` | 取决于 Runway model/version 的分辨率样式值，例如 `1280:768`、`768:1280`、`1280:720` 或 `720:1280` | `1280:768` | 请求值在最终媒体中可能会发生归一化；在依赖精确像素前，请先检查生成完成的视频。 | | 使用较旧兼容版本时的 `ratio` | `16:9`、`9:16`，或所选 model/version 接受的分辨率样式值 | `16:9` 或 `1280:768` | 在生产集成中，优先使用当前 Runway 的分辨率样式值。 | Runway 官方格式请求使用 `ratio`，而不是 `size`。请将分辨率样式的 ratio 值理解为其对应的 `WxH`：`1280:720` 表示目标为 `1280x720`，`720:1280` 表示目标为 `720x1280`，而 `1280:768` 仍可能根据所选 model/version 渲染为 `1280x720`。 ## 任务流程 使用源图片和可选的简短运动 Prompt 创建任务。 保存任务 `id` 以便后续轮询。 使用 [获取一个 Runway 任务](./runway-to-get-task-details)。如果第一次轮询返回 `task_not_exist`，请等待几秒后重试。 ## OpenAPI ````yaml api/openapi/video/runway/official-format/post-runway-images-raw-video.openapi.json POST /runwayml/v1/image_to_video openapi: 3.1.0 info: title: Image to Video API version: 1.0.0 description: >- Create a Runway image-to-video task through the official-format CometAPI route. servers: - url: https://api.cometapi.com security: - bearerAuth: [] paths: /runwayml/v1/image_to_video: post: summary: Create a Runway image-to-video task description: >- Submit a source image plus optional motion prompt and receive a task id for later polling. operationId: runway_images_raw_video parameters: - name: X-Runway-Version in: header required: true description: Runway version header, for example `2024-11-06`. schema: type: string requestBody: required: true content: application/json: schema: type: object required: - promptImage - model properties: promptImage: type: string description: Source image URL. default: >- https://cdn.britannica.com/70/234870-050-D4D024BB/Orange-colored-cat-yawns-displaying-teeth.jpg seed: type: integer description: 'Random seed for reproducible results. Range: 0–999999999.' model: type: string description: >- Runway image-to-video model ID. Choose an available model from the [Models page](/overview/models). default: gen3a_turbo promptText: type: string description: >- Text prompt describing the desired motion or scene. Maximum 512 characters. watermark: type: boolean description: Whether to add a watermark to the output video. default: false duration: type: integer description: >- Video duration in seconds. Runway support is model/version dependent; use 5 or 10 for the broadest compatibility. CometAPI forwards this value to Runway. default: 5 ratio: type: string description: >- Requested output ratio. Accepted values are Runway model/version dependent. With X-Runway-Version 2024-11-06, use a resolution-style value accepted by the selected model, such as 1280:768, 768:1280, 1280:720, or 720:1280. Read these as WxH targets, but completed media may normalize, so inspect the returned file before relying on exact pixels. default: '1280:768' default: promptImage: >- https://cdn.britannica.com/70/234870-050-D4D024BB/Orange-colored-cat-yawns-displaying-teeth.jpg seed: 1 model: gen3a_turbo promptText: A calm camera move. watermark: false duration: 5 ratio: '1280:768' examples: Default: summary: Default value: promptImage: >- https://cdn.britannica.com/70/234870-050-D4D024BB/Orange-colored-cat-yawns-displaying-teeth.jpg seed: 1 model: gen3a_turbo promptText: A calm camera move. watermark: false duration: 5 ratio: '1280:768' responses: '200': description: Task accepted. content: application/json: schema: type: object required: - id properties: id: type: string example: id: d0658ae1-bbdd-4adc-aaba-fd8070e14d79 x-codeSamples: - lang: Shell label: Default source: | curl https://api.cometapi.com/runwayml/v1/image_to_video \ -H "Authorization: Bearer $COMETAPI_KEY" \ -H "Content-Type: application/json" \ -d '{ "promptImage": "https://your-image-host/first-frame.png", "promptText": "A calm camera move.", "model": "gen3a_turbo", "ratio": "1280:768", "duration": 5 }' - lang: Python label: Default source: > import os import requests response = requests.post( "https://api.cometapi.com/runwayml/v1/image_to_video", headers={"Authorization": "Bearer " + os.environ["COMETAPI_KEY"]}, json={ "promptImage": "https://your-image-host/first-frame.png", "promptText": "A calm camera move.", "model": "gen3a_turbo", "ratio": "1280:768", "duration": 5 }, ) task = response.json() print(task["id"]) # poll GET /runwayml/v1/tasks/{id} until the output array appears - lang: JavaScript label: Default source: > const response = await fetch("https://api.cometapi.com/runwayml/v1/image_to_video", { method: "POST", headers: { Authorization: `Bearer ${process.env.COMETAPI_KEY}`, "Content-Type": "application/json", }, body: JSON.stringify({ "promptImage": "https://your-image-host/first-frame.png", "promptText": "A calm camera move.", "model": "gen3a_turbo", "ratio": "1280:768", "duration": 5 }), }); const task = await response.json(); console.log(task.id); // poll GET /runwayml/v1/tasks/{id} until the output array appears components: securitySchemes: bearerAuth: type: http scheme: bearer description: Bearer token authentication. Use your CometAPI key. ````