> ## Documentation Index
> Fetch the complete documentation index at: https://dripart-codex-simplify-get-started.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Use Ultimate Image Upscaler with Comfy Router

> Call wavespeed/ultimate-image-upscaler through Comfy Router: endpoint, request shape and the response Router returns.

API Reference for `wavespeed/ultimate-image-upscaler`, served by Comfy Router from WaveSpeed.

## Quick start

Create a key in [your Comfy workspace](https://platform.comfy.org/profile/api-keys) and export it as `COMFY_API_KEY`. The Python and TypeScript snippets use the Comfy SDKs (`pip install comfy-sdk`, `npm install @comfyorg/sdk`); the cURL snippet is the same call over raw HTTP.

**Model ID:** `wavespeed/ultimate-image-upscaler`

**Endpoint:** `POST https://api.comfy.org/v2/models/wavespeed/ultimate-image-upscaler`

<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(
          "wavespeed/ultimate-image-upscaler",
          {
              "image": "https://images.pexels.com/photos/346529/pexels-photo-346529.jpeg",
              "target_resolution": "4k",
          },
      )

  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("wavespeed/ultimate-image-upscaler", {
    image: "https://images.pexels.com/photos/346529/pexels-photo-346529.jpeg",
    target_resolution: "4k",
  });

  console.log(data);
  ```

  ```bash cURL theme={null}
  curl https://api.comfy.org/v2/models/wavespeed/ultimate-image-upscaler \
    -H "X-API-Key: $COMFY_API_KEY" \
    -H "Idempotency-Key: $(uuidgen)" \
    -H "Content-Type: application/json" \
    -d "{\"image\": \"https://images.pexels.com/photos/346529/pexels-photo-346529.jpeg\", \"target_resolution\": \"4k\"}"
  ```
</CodeGroup>

## Schema

### Input

<ParamField body="enable_base64_output" type="boolean" default="false">
  If enabled, the output will be encoded into a BASE64 string instead of a URL.
</ParamField>

<ParamField body="image" type="string" required>
  The URL of the image to upscale.
</ParamField>

<ParamField body="output_format" type="string" default="&#x22;jpeg&#x22;">
  The format of the output image.

  Possible values: `jpeg`, `png`, `webp`
</ParamField>

<ParamField body="target_resolution" type="string" default="&#x22;4k&#x22;">
  The target resolution of the output image.

  Possible values: `2k`, `4k`, `8k`
</ParamField>

Generated from the schema Router serves at `GET /v2/models/wavespeed/ultimate-image-upscaler/openapi.json`, the same document it validates a call against before the request reaches the provider.

### Output

<ResponseField name="code" type="integer">
  WavespeedAI's own envelope status code, mirroring an HTTP status (200 on the document this schema describes). Wavespeed reports some failures here rather than in the transport status.
</ResponseField>

<ResponseField name="data" type="object" required />

<ResponseField name="data.created_at" type="string">
  ISO-8601 timestamp of when Wavespeed created the prediction.
</ResponseField>

<ResponseField name="data.error" type="string">
  Wavespeed's free-text failure reason, an empty string when there is none. A prediction that genuinely failed reaches a Router caller as a Comfy Router error rather than as this document.
</ResponseField>

<ResponseField name="data.id" type="string">
  Wavespeed's identifier for the prediction Router submitted and polled.
</ResponseField>

<ResponseField name="data.model" type="string">
  The Wavespeed model id the prediction ran on.
</ResponseField>

<ResponseField name="data.outputs" type="string[]" required>
  The finished generation. Present and non-empty on the document Router returns; this list IS the result. Each element is a URL to the generated content - an MP4 for `wavespeed/flashvsr`, an image for the two upscalers - or, for the two image ids when the request set `enable_base64_output`, the base64-encoded bytes themselves. The links are Wavespeed's own and expire.
</ResponseField>

<ResponseField name="data.status" type="string" required>
  The prediction's terminal state as Wavespeed spelled it. Not narrowed to an enum here: Router forwards the value unchanged and the poll classifier lower-cases before comparing, so a success can legitimately arrive as `completed`, `succeeded`, `success` or `done`, in any case.
</ResponseField>

<ResponseField name="data.timings" type="object">
  Wavespeed's own timing measurements.
</ResponseField>

<ResponseField name="data.timings.inference" type="integer">
  Inference time in milliseconds. Wavespeed's number, not the Comfy charge.
</ResponseField>

<ResponseField name="data.urls" type="object">
  Wavespeed's own links for the prediction.
</ResponseField>

<ResponseField name="data.urls.get" type="string">
  The prediction-result URL Router polled.
</ResponseField>

<ResponseField name="message" type="string">
  Envelope status message, for example `success`.
</ResponseField>

## Examples

### Input

```json theme={null}
{
  "image": "https://images.pexels.com/photos/346529/pexels-photo-346529.jpeg",
  "target_resolution": "4k"
}
```

### Output

```json theme={null}
{
  "code": 200,
  "data": {
    "created_at": "2027-01-01T00:00:00Z",
    "error": "",
    "id": "3f6c1a90-2b47-4d18-9a55-7c0e8b21d4f3",
    "outputs": [
      "https://example.invalid/wavespeed/ultimate-image-upscaler/upscaled.png"
    ],
    "status": "completed",
    "timings": {
      "inference": 9100
    }
  },
  "message": "success"
}
```

## Before you ship

The SDKs create an `Idempotency-Key` and reuse it for automatic retries. For manual retries, reuse the original key. Router can hold the connection for up to 10 minutes.

When a request fails, Router sends an `X-Comfy-Error-Type` response header explaining why. A `422` means Router rejected the input before calling the provider. Download generated assets promptly because [result URLs can expire](/development/comfy-router/reference#result-assets).

<CardGroup cols={3}>
  <Card title="Headers" icon="list" href="/development/comfy-router/headers">
    Authentication, idempotency, request IDs, error buckets, retry pacing, spend limits.
  </Card>

  <Card title="Using the Router API" icon="code" href="/development/comfy-router/api">
    Model discovery, validation errors, retries, and billing.
  </Card>

  <Card title="Limitations" icon="triangle-exclamation" href="/development/comfy-router/limitations">
    What Router does not do today, and what to use instead.
  </Card>
</CardGroup>