Name: zf-kbot ComfyUI Text Unblur API
Brand: magicapi
SKU: api-magicapi-text-unblur-ai-api-zf-kbot-comfyui-text-unblur
Availability: InStock
Author: API Market

Shashank Agarwal

# 🔍 Text Unblur API (zf-kbot ComfyUI Text Unblur)

## Overview
ComfyUI Text Unblur is an image workflow published by zf-kbot for unblurring text in images. Send a blurry photo or scan, such as an invoice or a sign, and the model returns a sharper version of the image.

The only required input is `image`. The other fields set the output size and trade speed against GPU memory. Each request returns a list of image URLs; the example returned one image.

## Features
- **One input**: send an image URL; every other field has a default.
- **Output size by pixel count**: `total_pixels` (default 4194304, about 2048 x 2048) sets the target pixel count of the output, from 262144 to 10000000. The model calculates the resolution from it.
- **Speed and memory settings**: `batch_size`, `blocks_to_swap`, `preserve_vram` and `offload_io_components` trade processing speed against GPU memory.
- **Debug output**: `enable_debug` turns on the workflow's debug mode.

## Use Cases
1. **Blurry documents**: make invoices, receipts and forms photographed out of focus readable again.
2. **Before OCR**: sharpen text in an image before sending it to a text extraction service.
3. **Signs and labels**: clean up blurred text in photos of signs, packaging and screens.
4. **Archive scans**: improve soft scans of printed pages.

## Visual Examples
### Example Input
Image (a blurred invoice):

![Example input: a photo of an invoice with blurred text](https://blog.api.market/wp-content/uploads/2026/11/text-unblur-blurred-invoice-w15-input-api-market.jpg)

Settings: `batch_size` `1`, `resolution` `1440`, `blocks_to_swap` `16`, `offload_io_components` `true`, `preserve_vram` `false`, `enable_debug` `false`. `total_pixels` was left at its default (4194304).

### Example Output
![ComfyUI Text Unblur output for the blurred invoice](https://blog.api.market/wp-content/uploads/2026/11/comfyui-text-unblur-output-zpmbb6r0-api-market.jpg)

## Input Parameters
| Field | Type | Required | Default | Allowed values | Description |
| --- | --- | --- | --- | --- | --- |
| `image` | string (URL) | Yes |  |  | An input image |
| `total_pixels` | integer | No | `4194304` | 262144 to 10000000 | Target total pixel count for the image (the resolution is calculated from this) |
| `resolution` | integer | No | `1024` | 512 to 2048 | Output resolution (higher = better quality but slower). Overridden by the `total_pixels` calculation |
| `batch_size` | integer | No | `2` | 1 to 4 | Batch size for processing (higher = faster but uses more VRAM) |
| `blocks_to_swap` | integer | No | `16` | 8 to 32 | Number of blocks to swap (lower = faster but may use more VRAM) |
| `preserve_vram` | boolean | No | `false` |  | Preserve VRAM (slower but uses less memory) |
| `offload_io_components` | boolean | No | `true` |  | Offload IO components (faster processing) |
| `enable_debug` | boolean | No | `false` |  | Debug mode |

## Pricing
- **Pay As You Go (PAYG) pricing**: you only pay for what you use.
- **Price**: $0.019 per API unit.
- **1 API unit = 1 successful request with up to 17 seconds of processing.** A longer job bills one more unit for each started block of 17 seconds (for example, 30 seconds of processing is 2 units, $0.038).
- Larger outputs take longer to process.
- **Example cost**: the example request took 13.07 seconds of processing, which is 1 unit, so $0.019.
- **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/text-unblur-ai-api-zf-kbot-comfyui-text-unblur`

### 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 1 second 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/text-unblur-ai-api-zf-kbot-comfyui-text-unblur/predictions" \
  -H "Content-Type: application/json" \
  -H "x-api-market-key: YOUR_API_MARKET_KEY" \
  -d '{
    "version": "eba0d1de8de9bf762190da9523704b5e1230c2430bf8e65b26ed6a6aa0cf15a6",
    "input": {
      "image": "https://blog.api.market/wp-content/uploads/2026/11/text-unblur-blurred-invoice-w15-input-api-market.jpg",
      "batch_size": 1,
      "resolution": 1440,
      "enable_debug": false,
      "preserve_vram": false,
      "blocks_to_swap": 16,
      "offload_io_components": true
    }
  }'
```

Response (201 Created):
```json
{
  "id": "zpmbb6r0thrmy0d1mvr8pnvqr8",
  "version": "eba0d1de8de9bf762190da9523704b5e1230c2430bf8e65b26ed6a6aa0cf15a6",
  "status": "starting",
  "created_at": "2026-11-04T14:21:49.140Z"
}
```

#### Check Prediction Status
```bash
curl -X GET "https://prod.api.market/api/v1/magicapi/text-unblur-ai-api-zf-kbot-comfyui-text-unblur/predictions/{id}" \
  -H "x-api-market-key: YOUR_API_MARKET_KEY"
```

Response when the prediction has finished (200 OK):
```json
{
  "id": "zpmbb6r0thrmy0d1mvr8pnvqr8",
  "status": "succeeded",
  "output": [
    "https://blog.api.market/wp-content/uploads/2026/11/comfyui-text-unblur-output-zpmbb6r0-api-market.jpg"
  ],
  "error": null,
  "created_at": "2026-11-04T14:21:49.140Z",
  "started_at": "2026-11-04T14:21:49.157Z",
  "completed_at": "2026-11-04T14:22:02.225Z"
}
```

`output` is a list of image URLs. The example returned one 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 `batch_size` above 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/text-unblur-ai-api-zf-kbot-comfyui-text-unblur";

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: "eba0d1de8de9bf762190da9523704b5e1230c2430bf8e65b26ed6a6aa0cf15a6", 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 = 1000;
  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/2026/11/text-unblur-blurred-invoice-w15-input-api-market.jpg",
  "batch_size": 1,
  "resolution": 1440,
  "enable_debug": false,
  "preserve_vram": false,
  "blocks_to_swap": 16,
  "offload_io_components": true
}).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/text-unblur-ai-api-zf-kbot-comfyui-text-unblur"


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": "eba0d1de8de9bf762190da9523704b5e1230c2430bf8e65b26ed6a6aa0cf15a6", "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 = 1
    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/2026/11/text-unblur-blurred-invoice-w15-input-api-market.jpg",
    "batch_size": 1,
    "resolution": 1440,
    "enable_debug": False,
    "preserve_vram": False,
    "blocks_to_swap": 16,
    "offload_io_components": True
}))
```

## FAQ
- **Which field sets the output size?**
  - `total_pixels`. The model calculates the resolution from it, and this overrides `resolution`. The default 4194304 is about 2048 x 2048 pixels.
- **Do I need to change the memory settings?**
  - No. `batch_size`, `blocks_to_swap`, `preserve_vram` and `offload_io_components` have working defaults; they only change speed and GPU memory use.
- **How much does one image cost?**
  - $0.019 for each started block of 17 seconds of processing. The example invoice took 13.07 seconds, so it cost 1 unit ($0.019).
- **Does it extract the text?**
  - No. It returns an image. Send the result to an OCR service if you need the text as characters.
- **What if my prediction fails?**
  - Failed predictions are not billed. Read the `error` field, adjust the input and try again.

## Contact Us
If you have any questions, reach out to us through the chat on the bottom right of the page.


Send a blurry image of a document, receipt or sign and get back a sharper version with the ComfyUI Text Unblur workflow. $0.019 per request of up to 17 seconds of processing, pay as you go.