> ## Documentation Index
> Fetch the complete documentation index at: https://dripart-matt-router-queue-preview.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Use Krea 2 Large with Comfy Router

> Call krea/krea-2-large through Comfy Router: endpoint, request shape and the response Router returns.

API Reference for `krea/krea-2-large`, served by Comfy Router from Krea.

## 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:** `krea/krea-2-large`

**Endpoint:** `POST https://api.comfy.org/v2/models/krea/krea-2-large`

<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(
              "krea/krea-2-large",
              {
                  "aspect_ratio": "1:1",
                  "prompt": "a red circle",
                  "resolution": "1K",
              },
          )

      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("krea/krea-2-large", {
        aspect_ratio: "1:1",
        prompt: "a red circle",
        resolution: "1K",
      });

      console.log(data);
      ```

      ```bash cURL theme={null}
      curl https://api.comfy.org/v2/models/krea/krea-2-large \
        -H "X-API-Key: $COMFY_API_KEY" \
        -H "Idempotency-Key: $(uuidgen)" \
        -H "Content-Type: application/json" \
        -d "{\"aspect_ratio\": \"1:1\", \"prompt\": \"a red circle\", \"resolution\": \"1K\"}"
      ```
    </CodeGroup>
  </Tab>

  <Tab title="Queue and collect later">
    <Note>
      Queued delivery is rolling out per workspace. Until yours is enabled, the submit route answers `403` with `X-Comfy-Error-Type: not_enabled`. Nothing about the request is wrong, and the same body works through the synchronous route in the meantime.
    </Note>

    The same body, sent to `POST https://api.comfy.org/v2/models/krea/krea-2-large/requests`. Router answers `201` with a `request_id` as soon as the run is admitted, and the result is collected once it is ready, from this process or another one. [Queued delivery](/development/comfy-router/queue) walks through status, cancellation and collection.

    <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(
              "krea/krea-2-large",
              {
                  "aspect_ratio": "1:1",
                  "prompt": "a red circle",
                  "resolution": "1K",
              },
          )
          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("krea/krea-2-large", {
        aspect_ratio: "1:1",
        prompt: "a red circle",
        resolution: "1K",
      });
      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/krea/krea-2-large/requests \
        -H "X-API-Key: $COMFY_API_KEY" \
        -H "Idempotency-Key: $(uuidgen)" \
        -H "Content-Type: application/json" \
        -d "{\"aspect_ratio\": \"1:1\", \"prompt\": \"a red circle\", \"resolution\": \"1K\"}"

      # 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/krea/krea-2-large/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/krea/krea-2-large/requests/$REQUEST_ID \
        -H "X-API-Key: $COMFY_API_KEY"
      ```
    </CodeGroup>
  </Tab>
</Tabs>

## Schema

### Input

<ParamField body="aspect_ratio" type="string" required>
  Aspect ratio. One of: 1:1, 4:3, 3:2, 16:9, 2.35:1, 4:5, 2:3, 9:16.

  Possible values: `1:1`, `4:3`, `3:2`, `16:9`, `2.35:1`, `4:5`, `2:3`, `9:16`
</ParamField>

<ParamField body="creativity" type="string" default="&#x22;medium&#x22;">
  Prompt interpretation strength: raw=0, low=10, medium=50, high=100.

  Possible values: `raw`, `low`, `medium`, `high`
</ParamField>

<ParamField body="image_style_references" type="object[]">
  Style references to use for the generation
</ParamField>

<ParamField body="image_style_references[].strength" type="number" required>
  Range: `-2` to `2`

  Format: `double`
</ParamField>

<ParamField body="image_style_references[].url" type="string (uri)">
  Format: `uri`
</ParamField>

<ParamField body="moodboards" type="object[]">
  Moodboards to use for generation. Currently limited to one moodboard.
</ParamField>

<ParamField body="moodboards[].id" type="string (uuid)" required>
  Format: `uuid`
</ParamField>

<ParamField body="moodboards[].strength" type="number" default="0.35">
  Range: `-0.5` to `1.5`

  Format: `double`
</ParamField>

<ParamField body="prompt" type="string" required />

<ParamField body="resolution" type="string" required>
  Resolution scale. One of: 1K.

  Possible values: `1K`
</ParamField>

<ParamField body="seed" type="number" />

<ParamField body="styles" type="object[]">
  Styles (typically LoRAs) to use for the generation
</ParamField>

<ParamField body="styles[].id" type="string" required />

<ParamField body="styles[].strength" type="number" required>
  Range: `-2` to `2`

  Format: `double`
</ParamField>

Generated from the schema Router serves at `GET /v2/models/krea/krea-2-large/openapi.json`, the same document it validates a call against before the request reaches the provider.

### Output

<ResponseField name="completed_at" type="string (date-time)" required>
  Format: `date-time`
</ResponseField>

<ResponseField name="created_at" type="string (date-time)" required>
  Format: `date-time`
</ResponseField>

<ResponseField name="job_id" type="string (uuid)" required>
  Format: `uuid`
</ResponseField>

<ResponseField name="result" type="object" required>
  The finished generation. Not nullable here, unlike on `KreaJob`: a terminal job whose `result` carries no `urls` is answered as a Comfy Router error, so a `200` always carries it.
</ResponseField>

<ResponseField name="result.style_id" type="string">
  Set by loraTraining jobs rather than by a generation; a `200` for these models carries `urls`.
</ResponseField>

<ResponseField name="result.urls" type="string (uri)[]" required>
  The generated images, as downloadable links. At least one, because a `completed` job with an empty `urls` is `success_without_output` and never reaches this document.
</ResponseField>

<ResponseField name="status" type="string" required>
  Always `completed` on this document: it is the only status `classifyKrea` answers `succeeded` on, and Krea's vocabulary is matched without a case fold.

  Possible values: `completed`
</ResponseField>

## Examples

### Input

```json theme={null}
{
  "aspect_ratio": "1:1",
  "prompt": "a red circle",
  "resolution": "1K"
}
```

### Output

```json theme={null}
{
  "completed_at": "2027-01-01T00:00:37Z",
  "created_at": "2027-01-01T00:00:00Z",
  "job_id": "7f1c2e84-5b90-4a37-8d61-2c0f9ab4e153",
  "result": {
    "urls": [
      "https://example.invalid/krea/krea-2/generated.png"
    ]
  },
  "status": "completed"
}
```

## 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>