Use AI Image Upscaler Precision V2 with Comfy Router

Call freepik/ai-image-upscaler-precision-v2 through Comfy Router: endpoint, request shape and the response Router returns.

API Reference for freepik/ai-image-upscaler-precision-v2, served by Comfy Router from Freepik.

Quick start

Create a key in your Comfy workspace and export it as COMFY_API_KEY. The Python and TypeScript snippets use the Comfy SDKs (pip install comfy-sdk and npm install @comfyorg/sdk); the cURL snippet is the same call over raw HTTP.

Model ID: freepik/ai-image-upscaler-precision-v2

Endpoint: POST https://api.comfy.org/v2/models/freepik/ai-image-upscaler-precision-v2

Wait for the result

Python

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(
        "freepik/ai-image-upscaler-precision-v2",
        {
            "image": "https://img.magnific.com/free-photo/light-through-mountains_395237-33.jpg?semt=ais_hybrid&w=740&q=80",
            "scale_factor": 8,
        },
    )

print(result)

Queue and collect later

The same body, sent to POST https://api.comfy.org/v2/models/freepik/ai-image-upscaler-precision-v2/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 walks through status, cancellation and collection.

Python

import asyncio
from comfy_sdk import AsyncComfy

# Reads COMFY_API_KEY from the environment.
# Each submit() call mints its own Idempotency-Key and reuses it for automatic retries.
async def main():
    async with AsyncComfy() as client:
        handle = await client.models.submit(
            "freepik/ai-image-upscaler-precision-v2",
            {
                "image": "https://img.magnific.com/free-photo/light-through-mountains_395237-33.jpg?semt=ais_hybrid&w=740&q=80",
                "scale_factor": 8,
            },
        )
        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.
        async 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 = await handle.get()

    print(result)

asyncio.run(main())

Schema

Input

flavor · string

Image processing flavor:

• sublime: Optimized for artistic and illustrated images

• photo: Optimized for photographic images

• photo_denoiser: Specialized for photos with noise reduction

  Possible values: sublime, photo, photo_denoiser

image · string · required

Source image to upscale. Accepts either:

• A publicly accessible HTTPS URL pointing to the image
• A base64-encoded image string

scale_factor · integer

Image scaling factor. Determines how much larger the output will be compared to input.

Range: 2 to 16

sharpen · integer · default: "7"

Image sharpness intensity control. Higher values increase edge definition and clarity.

Range: 0 to 100

smart_grain · integer · default: "7"

Intelligent grain/texture enhancement. Higher values add more fine-grained texture.

Range: 0 to 100

ultra_detail · integer · default: "30"

Ultra detail enhancement level. Higher values create more intricate details.

Range: 0 to 100

webhook_url · string (uri)

Optional callback URL that will receive asynchronous notifications when the upscaling task completes.

Format: uri

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

Output

data · object · required

data.generated · string (uri)[] · required

The finished generation’s image URLs. Present and non-empty on the document Router returns; this list IS the result. The links are Freepik’s own and expire.

data.status · string · required

Possible values: COMPLETED

data.task_id · string (uuid)

Format: uuid

Examples

Input

{
  "image": "https://img.magnific.com/free-photo/light-through-mountains_395237-33.jpg?semt=ais_hybrid&w=740&q=80",
  "scale_factor": 8
}

Output

{
  "data": {
    "generated": [
      "https://example.invalid/freepik/ai-image-upscaler-precision-v2/upscaled.png"
    ],
    "status": "COMPLETED",
    "task_id": "046b6c7f-0b8a-43b9-b35d-6489e6daee91"
  }
}

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, and a 413 means the request body was larger than Router accepts. Download generated assets promptly because result URLs can expire.

Any size limit named in a field description above is the provider’s own bound on that field, quoted from the provider’s specification. Router applies a separate cap to the whole request body, which base64-encoded media counts against: see request body size.

This page documents one partner model called through Comfy Router. The same comfy-sdk / @comfyorg/sdk package also ships a second client, for running a whole ComfyUI workflow graph on Comfy Cloud: Comfy(api_key=...) / new Comfy({ apiKey }), with client.workflows, client.assets and client.jobs. See Comfy SDKs.

Headers

Authentication, idempotency, request IDs, error buckets, retry pacing, spend limits.

Using the Router API

Model discovery, validation errors, retries, and billing.

Limitations

What Router does not do today, and what to use instead.