> ## Documentation Index
> Fetch the complete documentation index at: https://dripart-chore-sync-comfy-api-v2-spec.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# 将 Ray 2 与 Comfy Router 配合使用

> 通过 Comfy Router 调用 luma/ray-2:endpoint、请求 shape 以及 Router 返回的响应。

`luma/ray-2` 的 API 参考，由 Comfy Router 从 Luma 提供。

## 快速开始

在[你的 Comfy 工作区](https://platform.comfy.org/profile/api-keys)中创建一个密钥，并将其导出为 `COMFY_API_KEY`。Python 和 TypeScript 代码片段使用 Comfy SDK（`pip install comfy-sdk`、`npm install @comfyorg/sdk`）；cURL 代码片段则是通过原始 HTTP 发起的同一调用。

**模型 ID：** `luma/ray-2`

**端点：** `POST https://api.comfy.org/v2/models/luma/ray-2`

<Tabs>
  <Tab title="Wait for the result">
    <CodeGroup>
      ```python Python theme={null}
      from comfy_sdk import Comfy

      # Reads COMFY_API_KEY from the environment.
      # The SDK automatically creates an idempotency key and reuses it for automatic retries.
      with Comfy() as client:
          result = client.models.run(
              "luma/ray-2",
              {
                  "aspect_ratio": "16:9",
                  "duration": "5s",
                  "prompt": "a single red maple leaf resting on a plain white background",
                  "resolution": "540p",
              },
          )

      print(result)
      ```

      ```typescript TypeScript theme={null}
      import { comfy } from "@comfyorg/sdk";

      // Reads COMFY_API_KEY from the environment.
      // The SDK automatically creates an idempotency key and reuses it for automatic retries.
      const { data } = await comfy.models.run("luma/ray-2", {
        aspect_ratio: "16:9",
        duration: "5s",
        prompt: "a single red maple leaf resting on a plain white background",
        resolution: "540p",
      });

      console.log(data);
      ```

      ```bash cURL theme={null}
      curl https://api.comfy.org/v2/models/luma/ray-2 \
        -H "X-API-Key: $COMFY_API_KEY" \
        -H "Idempotency-Key: $(uuidgen)" \
        -H "Content-Type: application/json" \
        -d "{\"aspect_ratio\": \"16:9\", \"duration\": \"5s\", \"prompt\": \"a single red maple leaf resting on a plain white background\", \"resolution\": \"540p\"}"
      ```
    </CodeGroup>
  </Tab>

  <Tab title="Queue and collect later">
    <CodeGroup>
      ```python Python theme={null}
      from comfy_sdk import Comfy

      # Reads COMFY_API_KEY from the environment.
      # Each submit() call mints its own Idempotency-Key and reuses it for automatic retries.
      with Comfy() as client:
          handle = client.models.submit(
              "luma/ray-2",
              {
                  "aspect_ratio": "16:9",
                  "duration": "5s",
                  "prompt": "a single red maple leaf resting on a plain white background",
                  "resolution": "540p",
              },
          )
          print("request_id:", handle.request_id)  # with the model ID, all another process needs

          # Poll until the request completes, waiting the Retry-After the server names.
          for update in handle.iter_events():
              print(update.status, update.queue_position)

          # The provider's own payload, the same value models.run() returns.
          # A request that failed or was cancelled raises the typed Router error here.
          result = handle.get()

      print(result)
      ```

      ```typescript TypeScript theme={null}
      import { comfy } from "@comfyorg/sdk";

      // Reads COMFY_API_KEY from the environment.
      // Each submit() call mints its own Idempotency-Key and reuses it for automatic retries.
      const handle = await comfy.models.submit("luma/ray-2", {
        aspect_ratio: "16:9",
        duration: "5s",
        prompt: "a single red maple leaf resting on a plain white background",
        resolution: "540p",
      });
      console.log("requestId:", handle.requestId); // with the model ID, all another process needs

      // Poll until the request completes, waiting the Retry-After the server names.
      for await (const update of handle.events()) {
        console.log(update.status, update.queuePosition);
      }

      // The same result models.run() returns. A request that failed or was cancelled rejects here.
      const result = await handle.get();

      console.log(result.data);
      ```

      ```bash cURL theme={null}
      # 1. Submit. Router answers 201 with request_id, status_url, response_url and cancel_url.
      curl https://api.comfy.org/v2/models/luma/ray-2/requests \
        -H "X-API-Key: $COMFY_API_KEY" \
        -H "Idempotency-Key: $(uuidgen)" \
        -H "Content-Type: application/json" \
        -d "{\"aspect_ratio\": \"16:9\", \"duration\": \"5s\", \"prompt\": \"a single red maple leaf resting on a plain white background\", \"resolution\": \"540p\"}"

      # 2. Poll until status is COMPLETED, waiting the Retry-After seconds each response names.
      REQUEST_ID="<request_id from the 201 body>"
      curl -i https://api.comfy.org/v2/models/luma/ray-2/requests/$REQUEST_ID/status \
        -H "X-API-Key: $COMFY_API_KEY"

      # 3. Collect. 200 with the model's native output, 202 with the status body while it is still running.
      curl https://api.comfy.org/v2/models/luma/ray-2/requests/$REQUEST_ID \
        -H "X-API-Key: $COMFY_API_KEY"
      ```
    </CodeGroup>
  </Tab>
</Tabs>

## Schema

### 输入

<ParamField body="aspect_ratio" type="string" required default="&#x22;16:9&#x22;">
  生成内容的宽高比

  可选值：`1:1`、`16:9`、`9:16`、`4:3`、`3:4`、`21:9`、`9:21`
</ParamField>

<ParamField body="callback_url" type="string (uri)">
  生成内容的回调 URL。当生成处于 dreaming、已完成或失败状态时，会向该回调 URL 发送一个携带 Generation 对象的 POST 请求

  格式：`uri`
</ParamField>

<ParamField body="duration" type="`5s`, `9s` | string" required />

<ParamField body="generation_type" type="string" default="&#x22;video&#x22;">
  可选值：`video`
</ParamField>

<ParamField body="keyframes" type="object">
  生成内容的关键帧
</ParamField>

<ParamField body="keyframes.frame0" type="object">
  关键帧可以是 Generation 引用、图像或视频
</ParamField>

<ParamField body="keyframes.frame1" type="object">
  关键帧可以是 Generation 引用、图像或视频
</ParamField>

<ParamField body="loop" type="boolean">
  是否循环播放视频
</ParamField>

<ParamField body="model" type="string">
  用于生成内容的视频模型。在 Comfy Router 的 `POST /v2/models/luma/{model}` 路由上，该字段由路径提供，因此不得发送；在 v1 的 `POST /proxy/luma/generations` 路由上，该字段为必填，且被限制为 LumaVideoModel 枚举（`ray-2`、`ray-flash-2`）。
</ParamField>

<ParamField body="prompt" type="string" required>
  生成内容的提示词
</ParamField>

<ParamField body="resolution" type="`540p`, `720p`, `1080p`, `4k` | string" required />

该文档由 Router 在 `GET /v2/models/luma/ray-2/openapi.json` 处提供的 schema 生成，同时也是它在请求到达提供商之前用于校验调用的同一份文档。

### 输出

<ResponseField name="assets" type="object">
  生成内容的资产
</ResponseField>

<ResponseField name="assets.image" type="string (uri)">
  图像的 URL

  格式：`uri`
</ResponseField>

<ResponseField name="assets.progress_video" type="string (uri)">
  进度视频的 URL

  格式：`uri`
</ResponseField>

<ResponseField name="assets.video" type="string (uri)">
  视频的 URL

  格式：`uri`
</ResponseField>

<ResponseField name="created_at" type="string (date-time)">
  生成内容的创建日期和时间

  格式：`date-time`
</ResponseField>

<ResponseField name="failure_reason" type="string">
  生成内容处于该状态的原因
</ResponseField>

<ResponseField name="generation_type" type="string">
  可选值：`video`、`image`
</ResponseField>

<ResponseField name="id" type="string (uuid)">
  生成内容的 ID

  格式：`uuid`
</ResponseField>

<ResponseField name="model" type="string">
  用于生成内容的模型
</ResponseField>

<ResponseField name="request" type="object">
  生成内容的请求
</ResponseField>

<ResponseField name="state" type="string">
  生成内容的状态

  可选值：`queued`、`dreaming`、`completed`、`failed`
</ResponseField>

## 示例

### 输入

```json theme={null}
{
  "aspect_ratio": "16:9",
  "duration": "5s",
  "prompt": "a single red maple leaf resting on a plain white background",
  "resolution": "540p"
}
```

### 输出

```json theme={null}
{
  "assets": {
    "video": "https://example.invalid/luma/ray-2/generated.mp4"
  },
  "created_at": "2027-01-01T00:00:00Z",
  "generation_type": "video",
  "id": "3f2a7c1e-8b40-4d59-9f6a-1c2d3e4f5a60",
  "model": "ray-2",
  "state": "completed"
}
```

## 发布前须知

SDK 会生成 `Idempotency-Key` 并在自动重试中复用它。手动重试时，请复用原始 key。Router 最长可保持连接 10 分钟。

请求失败时，Router 会发送 `X-Comfy-Error-Type` 响应头说明原因。`422` 表示 Router 在调用提供商之前就拒绝了输入。生成的资源请及时下载，因为[结果链接会过期](/zh/development/comfy-router/reference#结果资产)。

<CardGroup cols={3}>
  <Card title="请求头" icon="list" href="/zh/development/comfy-router/quickstart">
    身份验证、幂等性、请求 ID、错误分类、重试节奏、消费限额。
  </Card>

  <Card title="使用 Router API" icon="code" href="/zh/development/comfy-router/quickstart">
    模型发现、校验错误、重试与计费。
  </Card>

  <Card title="限制" icon="triangle-exclamation" href="/zh/development/comfy-router/limitations">
    Router 目前不支持的功能，以及替代方案。
  </Card>
</CardGroup>