> ## Documentation Index
> Fetch the complete documentation index at: https://docs.creatify.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Upscale image · Image to image

> AI-powered image upscaling with up to 4x resolution enhancement.

[← Quick Editing](/api-documentation/ai-generation/models/quick-editing)

**Model name:** `flux-vision-upscaler`\
**Generation type:** `image_to_image`\
**Endpoint:** [`POST /api/asset_generator/`](/api-reference/ai-generation/post-ai-generation)

## Pricing

**1.0** credits per output.

Prices are per output. When a request asks for several outputs, the charge is this price times the number of outputs.

## Quick start

The example uses sample media from our CDN. Swap in publicly accessible URLs for your own files.

<CodeGroup>
  ```bash cURL theme={null}
  curl --request POST \
    --url https://api.creatify.ai/api/asset_generator/ \
    --header 'Content-Type: application/json' \
    --header 'X-API-ID: your-api-id' \
    --header 'X-API-KEY: your-api-key' \
    --data '{
      "model_name": "flux-vision-upscaler",
      "input_params": {
        "image_url": "https://d35ghwdno3nak3.cloudfront.net/tutorial/avatar-aurora/recommendation-4.jpg"
      }
    }'
  ```

  ```python Python theme={null}
  import requests

  response = requests.post(
      "https://api.creatify.ai/api/asset_generator/",
      headers={"X-API-ID": "your-api-id", "X-API-KEY": "your-api-key"},
      json={
          "model_name": "flux-vision-upscaler",
          "input_params": {
              "image_url": "https://d35ghwdno3nak3.cloudfront.net/tutorial/avatar-aurora/recommendation-4.jpg"
          },
      },
  )
  print(response.json()["id"])
  ```
</CodeGroup>

## Input parameters

Send these fields in `input_params`.

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

<ParamField body="seed" type="object">
  The seed to use for the upscale. If not provided, a random seed will be used.
</ParamField>

<ParamField body="steps" type="integer" default={20}>
  Number of inference steps (4-50).

  Minimum: `4`.
  Maximum: `50`.
</ParamField>

<ParamField body="guidance" type="number" default={1}>
  CFG/guidance scale (1-4). Controls how closely the model follows the prompt.

  Minimum: `1`.
  Maximum: `4`.
</ParamField>

<ParamField body="creativity" type="number" default={0.3}>
  The creativity of the model. The higher the creativity, the more the model will deviate from the original. Refers to the denoise strength of the sampling.

  Minimum: `0`.
  Maximum: `1`.
</ParamField>

<ParamField body="upscale_factor" type="number" default={2}>
  The upscale factor (1-4x).

  Minimum: `1`.
  Maximum: `4`.
</ParamField>

<ParamField body="enable_safety_checker" type="boolean" default={true}>
  Whether to enable the safety checker.
</ParamField>

<Accordion title="Complete JSON schema">
  ```json theme={null}
  {
    "$schema": "http://json-schema.org/draft-07/schema#",
    "required": [
      "image_url"
    ],
    "properties": {
      "seed": {
        "title": "Seed",
        "description": "The seed to use for the upscale. If not provided, a random seed will be used.",
        "x-advance-settings": true
      },
      "steps": {
        "type": "integer",
        "title": "Steps",
        "default": 20,
        "maximum": 50,
        "minimum": 4,
        "description": "Number of inference steps (4-50)."
      },
      "guidance": {
        "type": "number",
        "title": "Guidance",
        "default": 1,
        "maximum": 4,
        "minimum": 1,
        "description": "CFG/guidance scale (1-4). Controls how closely the model follows the prompt."
      },
      "image_url": {
        "type": "string",
        "title": "Image Url",
        "description": "The URL of the image to upscale."
      },
      "creativity": {
        "type": "number",
        "title": "Creativity",
        "default": 0.3,
        "maximum": 1,
        "minimum": 0,
        "description": "The creativity of the model. The higher the creativity, the more the model will deviate from the original. Refers to the denoise strength of the sampling."
      },
      "upscale_factor": {
        "type": "number",
        "title": "Upscale Factor",
        "default": 2,
        "maximum": 4,
        "minimum": 1,
        "description": "The upscale factor (1-4x)."
      },
      "enable_safety_checker": {
        "type": "boolean",
        "title": "Enable Safety Checker",
        "default": true,
        "description": "Whether to enable the safety checker."
      }
    }
  }
  ```
</Accordion>

## Response

The request returns the task with `status: "initializing"`. Poll [GET /api/asset\_generator/\{id}/](/api-reference/ai-generation/get-ai-generation-) until `status` is `done` or `failed`, or pass a `webhook_url` to be notified. A finished task lists its files in `assets` and the credits it charged in `credits_used`.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.