Name: lucataco DemoFusion Enhance Image Upscaler and Enhancer API
Brand: magicapi
SKU: api-magicapi-image-to-image-enhancer-lucataco-demofusion-enhance
Availability: InStock
Author: API Market

Shashank Agarwal

# 🔍 Image Upscaler and Enhancer API (lucataco DemoFusion Enhance)

## Overview
DemoFusion Enhance by lucataco regenerates an input image at a larger size with the DemoFusion method on a diffusion model. Its developer describes it as an image-to-image enhancer.

Send an `image` and a `scale` factor of 1, 2 (default) or 4. A text `prompt` guides the new detail; set `auto_prompt` to `true` to describe the image automatically instead. Each request returns the URL of one image.

## Features
- **Scale factor**: `scale` of `1`, `2` (default) or `4` for the input image.
- **Prompt guided detail**: describe the image in `prompt`, or set `auto_prompt` to use an automatically generated description.
- **Negative prompt**: defaults to `blurry, ugly, duplicate, poorly drawn, deformed, mosaic`.
- **DemoFusion controls**: `stride`, `view_batch_size`, `multi_decoder`, `sigma` and three `cosine_scale` values for advanced tuning.
- **Seed**: set `seed` to reproduce a result.

## Use Cases
1. **Larger images for print or display**: enlarge a picture by 2x or 4x with regenerated detail.
2. **Sharper product and stock photos**: add detail to small source images.
3. **Enlarging generated art**: take a small AI image to a higher resolution.
4. **Wallpapers and backgrounds**: create bigger versions of existing images.

## Visual Examples
### Example Input
![Example input image for DemoFusion Enhance](https://blog.api.market/wp-content/uploads/2026/10/demofusion-enhance-input-w14-api-market.jpg)

Settings: `scale` 2, `auto_prompt` `true`, `negative_prompt` `blurry, ugly, duplicate, poorly drawn, deformed, mosaic`, `num_inference_steps` 40, `guidance_scale` 8.5, `stride` 64, `view_batch_size` 16, `multi_decoder` `false`, `cosine_scale_1` 3, `cosine_scale_2` 1, `cosine_scale_3` 1, `sigma` 0.8.

### Example Output
![DemoFusion Enhance output: the example input image regenerated at 2x scale](https://blog.api.market/wp-content/uploads/2026/10/demofusion-enhance-output-9epksgf3-api-market.jpg)

## Input Parameters
| Field | Type | Required | Default | Allowed values | Description |
| --- | --- | --- | --- | --- | --- |
| `image` | string (URL) | Yes |  |  | Input image (jpeg, png, gif or webp). |
| `scale` | integer | No | `2` | `1`, `2`, `4` | Scale factor for the input image. |
| `prompt` | string | No | `A high resolution photo` |  | Text prompt that guides the regenerated detail. |
| `auto_prompt` | boolean | No | `false` |  | Use an automatically generated description of the image instead of `prompt`. |
| `negative_prompt` | string | No | `blurry, ugly, duplicate, poorly drawn, deformed, mosaic` |  | Things to avoid in the output. |
| `num_inference_steps` | integer | No | `40` | 1 to 500 | Number of denoising steps. |
| `guidance_scale` | number | No | `8.5` | 1 to 50 | Scale for classifier-free guidance. |
| `view_batch_size` | integer | No | `16` |  | Batch size for multiple denoising paths. |
| `stride` | integer | No | `64` |  | Stride of the moving local patches. |
| `multi_decoder` | boolean | No | `false` |  | Use multiple decoders. |
| `cosine_scale_1` | number | No | `3` |  | Strength of the skip-residual. |
| `cosine_scale_2` | number | No | `1` |  | Strength of the dilated sampling. |
| `cosine_scale_3` | number | No | `1` |  | Strength of the Gaussian filter. |
| `sigma` | number | No | `0.8` |  | Standard value of the Gaussian filter. |
| `seed` | integer | No | none |  | Random seed. Leave unset to randomize the seed. |

## Pricing
- **Pay As You Go (PAYG) pricing**: you only pay for what you use.
- **Price**: $0.525 per API unit.
- **1 API unit = one request with up to 337 seconds of processing.** A request that takes longer is billed one more unit for every started 337-second block (for example, 337 to 674 seconds is 2 units, $1.05).
- A larger `scale` or more `num_inference_steps` take longer and can use more units.
- **Example cost**: the example request (`scale` 2, 40 steps) took 91.7 seconds of processing: 1 unit, $0.525.
- **Failed or cancelled predictions are not billed.**
- **GET requests to check prediction status** are free and don't count toward API unit usage.
- **No monthly subscription fee.**

## API Documentation

### Base URL
All API requests go to: `https://prod.api.market/api/v1/magicapi/image-to-image-enhancer-lucataco-demofusion-enhance`

### Authentication
Send your api.market API key in the `x-api-market-key` header:
```
x-api-market-key: YOUR_API_MARKET_KEY
```

### Asynchronous Processing
**IMPORTANT**: This API is asynchronous. The flow is:
1. Send a POST request to `/predictions`. A successful request returns **201 Created** with a prediction `id` and a `status` of `starting` or `processing`.
2. Poll GET `/predictions/{id}` with that ID.
3. Keep polling while `status` is `starting` or `processing`.
4. Stop when `status` is `succeeded` (read `output`), `failed` or `canceled` (read `error`).

A polling interval of 2 seconds and an overall timeout of 600 seconds (10 minutes) work well.

### Endpoints

#### Create a Prediction
```bash
curl -X POST "https://prod.api.market/api/v1/magicapi/image-to-image-enhancer-lucataco-demofusion-enhance/predictions" \
  -H "Content-Type: application/json" \
  -H "x-api-market-key: YOUR_API_MARKET_KEY" \
  -d '{
    "version": "5bcfe11066c820e8c08232c6efa3c8a7ab2cd667ad136ca173633f352170691e",
    "input": {
      "image": "https://blog.api.market/wp-content/uploads/2026/10/demofusion-enhance-input-w14-api-market.jpg",
      "scale": 2,
      "sigma": 0.8,
      "stride": 64,
      "auto_prompt": true,
      "multi_decoder": false,
      "cosine_scale_1": 3,
      "cosine_scale_2": 1,
      "cosine_scale_3": 1,
      "guidance_scale": 8.5,
      "negative_prompt": "blurry, ugly, duplicate, poorly drawn, deformed, mosaic",
      "view_batch_size": 16,
      "num_inference_steps": 40
    }
  }'
```

Response (201 Created):
```json
{
  "id": "9epksgf3gsrnc0d1f1ksrv88rr",
  "version": "5bcfe11066c820e8c08232c6efa3c8a7ab2cd667ad136ca173633f352170691e",
  "status": "starting",
  "created_at": "2026-10-26T13:30:36.991Z"
}
```

#### Check Prediction Status
```bash
curl -X GET "https://prod.api.market/api/v1/magicapi/image-to-image-enhancer-lucataco-demofusion-enhance/predictions/{id}" \
  -H "x-api-market-key: YOUR_API_MARKET_KEY"
```

Response when the prediction has finished (200 OK):
```json
{
  "id": "9epksgf3gsrnc0d1f1ksrv88rr",
  "status": "succeeded",
  "output": "https://blog.api.market/wp-content/uploads/2026/10/demofusion-enhance-output-9epksgf3-api-market.jpg",
  "error": null,
  "created_at": "2026-10-26T13:30:36.991Z",
  "started_at": "2026-10-26T13:34:08.501Z",
  "completed_at": "2026-10-26T13:35:40.171Z"
}
```

`output` is a single URL string pointing to the enhanced image.

### Status Codes
- **201 Created**: prediction created (POST `/predictions`). This is the normal success response.
- **200 OK**: prediction details returned (GET `/predictions/{id}`).
- **400 Bad Request**: invalid input, for example a missing `image` or a `scale` other than 1, 2 or 4.
- **401 Unauthorized**: missing or invalid API key.
- **404 Not Found**: no prediction with that ID.
- **429 Too Many Requests**: rate limit exceeded.
- **500 Internal Server Error** or **503 Service Unavailable**: temporary server problem; retry later.

## Rate Limits
Requests are rate limited to keep usage fair. If you receive a 429 response, wait and retry with exponential backoff.

## Error Handling
- Check the HTTP status code of every request and read the response body for the error message.
- A prediction can also end with `status` set to `failed`; the `error` field then explains why. Failed predictions are not billed.
- Retry 429, 500 and 503 responses with exponential backoff. Fix the input before retrying a 400.

## Implementation Guide
### Example Code

#### JavaScript
```javascript
const apiKey = "YOUR_API_MARKET_KEY";
const baseUrl = "https://prod.api.market/api/v1/magicapi/image-to-image-enhancer-lucataco-demofusion-enhance";

async function createAndWaitForPrediction(input) {
  const response = await fetch(`${baseUrl}/predictions`, {
    method: "POST",
    headers: {
      "Content-Type": "application/json",
      "x-api-market-key": apiKey
    },
    body: JSON.stringify({ version: "5bcfe11066c820e8c08232c6efa3c8a7ab2cd667ad136ca173633f352170691e", input })
  });

  if (response.status !== 201) {
    throw new Error(`API error: ${response.status} ${await response.text()}`);
  }

  const prediction = await response.json();
  return pollForResults(prediction.id);
}

const delay = (ms) => new Promise((resolve) => setTimeout(resolve, ms));

async function pollForResults(predictionId) {
  const maxTimeout = 600000;
  const pollInterval = 2000;
  const startTime = Date.now();

  while (Date.now() - startTime < maxTimeout) {
    const response = await fetch(`${baseUrl}/predictions/${predictionId}`, {
      headers: { "x-api-market-key": apiKey }
    });

    if (!response.ok) {
      throw new Error(`API error: ${response.status} ${await response.text()}`);
    }

    const prediction = await response.json();

    if (prediction.status === "succeeded") {
      return prediction.output;
    }

    if (prediction.status === "failed" || prediction.status === "canceled") {
      throw new Error(`Prediction ${prediction.status}: ${prediction.error || "Unknown error"}`);
    }

    await delay(pollInterval);
  }

  throw new Error("Prediction timed out after 10 minutes");
}

createAndWaitForPrediction({
  "image": "https://blog.api.market/wp-content/uploads/2026/10/demofusion-enhance-input-w14-api-market.jpg",
  "scale": 2,
  "sigma": 0.8,
  "stride": 64,
  "auto_prompt": true,
  "multi_decoder": false,
  "cosine_scale_1": 3,
  "cosine_scale_2": 1,
  "cosine_scale_3": 1,
  "guidance_scale": 8.5,
  "negative_prompt": "blurry, ugly, duplicate, poorly drawn, deformed, mosaic",
  "view_batch_size": 16,
  "num_inference_steps": 40
}).then((output) => console.log(output));
```

#### Python
```python
import time
import requests

API_KEY = "YOUR_API_MARKET_KEY"
BASE_URL = "https://prod.api.market/api/v1/magicapi/image-to-image-enhancer-lucataco-demofusion-enhance"


def create_and_wait_for_prediction(input_data):
    headers = {"Content-Type": "application/json", "x-api-market-key": API_KEY}
    response = requests.post(
        f"{BASE_URL}/predictions",
        headers=headers,
        json={"version": "5bcfe11066c820e8c08232c6efa3c8a7ab2cd667ad136ca173633f352170691e", "input": input_data},
    )

    if response.status_code != 201:
        raise Exception(f"API error: {response.status_code} {response.text}")

    return poll_for_results(response.json()["id"])


def poll_for_results(prediction_id):
    max_timeout = 600
    poll_interval = 2
    headers = {"x-api-market-key": API_KEY}
    start_time = time.time()

    while time.time() - start_time < max_timeout:
        response = requests.get(f"{BASE_URL}/predictions/{prediction_id}", headers=headers)

        if response.status_code != 200:
            raise Exception(f"API error: {response.status_code} {response.text}")

        prediction = response.json()

        if prediction["status"] == "succeeded":
            return prediction["output"]

        if prediction["status"] in ("failed", "canceled"):
            raise Exception(f"Prediction {prediction['status']}: {prediction.get('error') or 'Unknown error'}")

        time.sleep(poll_interval)

    raise Exception("Prediction timed out after 10 minutes")


print(create_and_wait_for_prediction({
    "image": "https://blog.api.market/wp-content/uploads/2026/10/demofusion-enhance-input-w14-api-market.jpg",
    "scale": 2,
    "sigma": 0.8,
    "stride": 64,
    "auto_prompt": True,
    "multi_decoder": False,
    "cosine_scale_1": 3,
    "cosine_scale_2": 1,
    "cosine_scale_3": 1,
    "guidance_scale": 8.5,
    "negative_prompt": "blurry, ugly, duplicate, poorly drawn, deformed, mosaic",
    "view_batch_size": 16,
    "num_inference_steps": 40
}))
```

## FAQ
- **How much larger is the output?**
  - Set by `scale`: 1, 2 (default) or 4 times the input image.
- **Do I need to write a prompt?**
  - No. `prompt` defaults to "A high resolution photo". Set `auto_prompt` to `true` to use an automatically generated description of your image instead.
- **Why does a request take a long time?**
  - The image is regenerated in patches by a diffusion model. Larger `scale` values and more steps take longer; one $0.525 unit covers up to 337 seconds of processing.
- **Which settings should I change first?**
  - `scale`, `prompt` and `num_inference_steps`. The `cosine_scale`, `sigma`, `stride` and `view_batch_size` values are advanced DemoFusion settings; the defaults are a good start.
- **Is the 201 response from POST an error?**
  - No. 201 Created means the prediction was accepted. Use the returned `id` to poll GET `/predictions/{id}` until `status` is `succeeded`, `failed` or `canceled`.
- **What if my prediction fails?**
  - Failed predictions are not billed. Read the `error` field, check that the image URL is reachable and try again.

## Contact Us
If you have any questions or need assistance, you can reach out to us through the embedded chat on the bottom right corner of the page or send an email to hello@magicapi.com.


Upscale and enhance images 2x or 4x with lucataco's DemoFusion Enhance, guided by a prompt or an automatic caption. $0.525 per call.