Name: ControlNet Preprocessors API: Edge, Depth and Pose Maps
Brand: magicapi
SKU: api-magicapi-ai-image-preprocessing-fofr-controlnet-preprocessors
Availability: InStock
Author: API Market

Shashank Agarwal

# 🧩 ControlNet Preprocessor API: Edge, Depth, Pose and Lineart Maps (fofr ControlNet Preprocessors)

## Overview
ControlNet Preprocessors by fofr runs up to 13 image preprocessors on one image in a single request: canny edges, content shuffle, face detection, HED, MiDaS depth, MLSD lines, OpenPose, PidiNet, NormalBae normals, lineart, anime lineart, SAM segmentation and LeReS depth.

Send an `image` and switch each preprocessor on or off with its boolean field. All 13 are on by default. The response is a list of image URLs, one for each preprocessor that ran.

## Features
- **13 preprocessors in one call**: `canny`, `content`, `face_detector`, `hed`, `midas`, `mlsd`, `open_pose`, `pidi`, `normal_bae`, `lineart`, `lineart_anime`, `sam`, `leres`.
- **Pick what you need**: set any preprocessor to `false` to skip it. Every field defaults to `true`.
- **Control images for generation**: the outputs are the edge, depth, pose, line and segmentation maps that ControlNet-style image generators take as conditioning input.
- **PNG outputs**: each map is returned as its own image URL.

## Use Cases
1. **ControlNet conditioning**: produce a depth map, pose skeleton or edge map from a reference photo, then use it to guide an image generator.
2. **Comparing preprocessors**: run all 13 at once to see which map keeps the structure you want.
3. **Line art from photos**: use `lineart` or `lineart_anime` to get clean outlines for colouring or illustration work.
4. **Pose and face layout**: use `open_pose` and `face_detector` to capture body and face positions from an image.

## Visual Examples
### Example Input
![Example input image sent to the preprocessors](https://blog.api.market/wp-content/uploads/2026/10/flux-red-cinema-output-y3zss6rq-api-market.jpg)

All 13 preprocessors were switched on.

### Example Output
The request returned 13 images, in this order:

1. Canny edges: ![Canny edge map](https://blog.api.market/wp-content/uploads/2026/10/controlnet-preprocessors-output-1-k5mx9v4b-api-market.png)
2. Content shuffle: ![Content shuffle map](https://blog.api.market/wp-content/uploads/2026/10/controlnet-preprocessors-output-2-k5mx9v4b-api-market.png)
3. Face detector: ![Face detection map](https://blog.api.market/wp-content/uploads/2026/10/controlnet-preprocessors-output-3-k5mx9v4b-api-market.png)
4. HED: ![HED soft edge map](https://blog.api.market/wp-content/uploads/2026/10/controlnet-preprocessors-output-4-k5mx9v4b-api-market.png)
5. MiDaS depth: ![MiDaS depth map](https://blog.api.market/wp-content/uploads/2026/10/controlnet-preprocessors-output-5-k5mx9v4b-api-market.png)
6. MLSD lines: ![MLSD straight line map](https://blog.api.market/wp-content/uploads/2026/10/controlnet-preprocessors-output-6-k5mx9v4b-api-market.png)
7. OpenPose: ![OpenPose skeleton map](https://blog.api.market/wp-content/uploads/2026/10/controlnet-preprocessors-output-7-k5mx9v4b-api-market.png)
8. PidiNet: ![PidiNet soft edge map](https://blog.api.market/wp-content/uploads/2026/10/controlnet-preprocessors-output-8-k5mx9v4b-api-market.png)
9. NormalBae: ![NormalBae normal map](https://blog.api.market/wp-content/uploads/2026/10/controlnet-preprocessors-output-9-k5mx9v4b-api-market.png)
10. Lineart: ![Lineart map](https://blog.api.market/wp-content/uploads/2026/10/controlnet-preprocessors-output-10-k5mx9v4b-api-market.png)
11. Lineart anime: ![Anime lineart map](https://blog.api.market/wp-content/uploads/2026/10/controlnet-preprocessors-output-11-k5mx9v4b-api-market.png)
12. SAM: ![SAM segmentation map](https://blog.api.market/wp-content/uploads/2026/10/controlnet-preprocessors-output-12-k5mx9v4b-api-market.png)
13. LeReS depth: ![LeReS depth map](https://blog.api.market/wp-content/uploads/2026/10/controlnet-preprocessors-output-13-k5mx9v4b-api-market.png)

## Input Parameters
| Field | Type | Required | Default | Allowed values | Description |
| --- | --- | --- | --- | --- | --- |
| `image` | string (URL) | Yes |  |  | Image to preprocess |
| `canny` | boolean | No | `true` |  | Run canny edge detection |
| `content` | boolean | No | `true` |  | Run content shuffle detection |
| `face_detector` | boolean | No | `true` |  | Run face detection |
| `hed` | boolean | No | `true` |  | Run HED detection |
| `midas` | boolean | No | `true` |  | Run MiDaS detection |
| `mlsd` | boolean | No | `true` |  | Run MLSD detection |
| `open_pose` | boolean | No | `true` |  | Run OpenPose detection |
| `pidi` | boolean | No | `true` |  | Run PidiNet detection |
| `normal_bae` | boolean | No | `true` |  | Run NormalBae detection |
| `lineart` | boolean | No | `true` |  | Run Lineart detection |
| `lineart_anime` | boolean | No | `true` |  | Run LineartAnime detection |
| `sam` | boolean | No | `true` |  | Run SAM detection |
| `leres` | boolean | No | `true` |  | Run LeReS detection |

## Pricing
- **Pay As You Go (PAYG) pricing**: you only pay for what you use.
- **Price**: $0.064 per API unit.
- **1 API unit = 1 request with up to 59 seconds of processing.** A request that takes longer is billed one more unit for each started 59-second block (for example, 70 seconds of processing is 2 units, $0.128).
- Turning preprocessors off shortens processing.
- The example request (all 13 preprocessors) took 8.2 seconds of processing, so it was billed 1 unit ($0.064).
- **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/ai-image-preprocessing-fofr-controlnet-preprocessors`

### 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/ai-image-preprocessing-fofr-controlnet-preprocessors/predictions" \
  -H "Content-Type: application/json" \
  -H "x-api-market-key: YOUR_API_MARKET_KEY" \
  -d '{
    "version": "f6584ef76cf07a2014ffe1e9bdb1a5cfa714f031883ab43f8d4b05506625988e",
    "input": {
      "hed": true,
      "sam": true,
      "mlsd": true,
      "pidi": true,
      "canny": true,
      "image": "https://blog.api.market/wp-content/uploads/2026/10/flux-red-cinema-output-y3zss6rq-api-market.jpg",
      "leres": true,
      "midas": true,
      "content": true,
      "lineart": true,
      "open_pose": true,
      "normal_bae": true,
      "face_detector": true,
      "lineart_anime": true
    }
  }'
```

Response (201 Created):
```json
{
  "id": "k5mx9v4b75rmt0d1d9jrxj80hr",
  "version": "f6584ef76cf07a2014ffe1e9bdb1a5cfa714f031883ab43f8d4b05506625988e",
  "status": "starting",
  "created_at": "2026-10-23T20:13:22.254Z"
}
```

#### Check Prediction Status
```bash
curl -X GET "https://prod.api.market/api/v1/magicapi/ai-image-preprocessing-fofr-controlnet-preprocessors/predictions/{id}" \
  -H "x-api-market-key: YOUR_API_MARKET_KEY"
```

Response when the prediction has finished (200 OK):
```json
{
  "id": "k5mx9v4b75rmt0d1d9jrxj80hr",
  "status": "succeeded",
  "output": [
    "https://blog.api.market/wp-content/uploads/2026/10/controlnet-preprocessors-output-1-k5mx9v4b-api-market.png",
    "https://blog.api.market/wp-content/uploads/2026/10/controlnet-preprocessors-output-2-k5mx9v4b-api-market.png",
    "https://blog.api.market/wp-content/uploads/2026/10/controlnet-preprocessors-output-3-k5mx9v4b-api-market.png",
    "https://blog.api.market/wp-content/uploads/2026/10/controlnet-preprocessors-output-4-k5mx9v4b-api-market.png",
    "https://blog.api.market/wp-content/uploads/2026/10/controlnet-preprocessors-output-5-k5mx9v4b-api-market.png",
    "https://blog.api.market/wp-content/uploads/2026/10/controlnet-preprocessors-output-6-k5mx9v4b-api-market.png",
    "https://blog.api.market/wp-content/uploads/2026/10/controlnet-preprocessors-output-7-k5mx9v4b-api-market.png",
    "https://blog.api.market/wp-content/uploads/2026/10/controlnet-preprocessors-output-8-k5mx9v4b-api-market.png",
    "https://blog.api.market/wp-content/uploads/2026/10/controlnet-preprocessors-output-9-k5mx9v4b-api-market.png",
    "https://blog.api.market/wp-content/uploads/2026/10/controlnet-preprocessors-output-10-k5mx9v4b-api-market.png",
    "https://blog.api.market/wp-content/uploads/2026/10/controlnet-preprocessors-output-11-k5mx9v4b-api-market.png",
    "https://blog.api.market/wp-content/uploads/2026/10/controlnet-preprocessors-output-12-k5mx9v4b-api-market.png",
    "https://blog.api.market/wp-content/uploads/2026/10/controlnet-preprocessors-output-13-k5mx9v4b-api-market.png"
  ],
  "error": null,
  "created_at": "2026-10-23T20:13:22.254Z",
  "started_at": "2026-10-23T20:13:23.254Z",
  "completed_at": "2026-10-23T20:13:32.254Z"
}
```

`output` is an array of image URLs, one per preprocessor that ran. Each file is named after its preprocessor (for example `canny.png`, `midas.png`), so match maps by file name rather than by position when you switch some preprocessors off.

### 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 preprocessor field that is not a boolean.
- **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
All plans allow 10 requests per second. Requests above that return `429 Too Many Requests`; back off before retrying and honour any `Retry-After` header. Polling a prediction with GET is free but still counts toward the per-second limit, so poll every 1 to 5 seconds rather than in a tight loop.

## 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 (for example, an image URL that cannot be downloaded). 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/ai-image-preprocessing-fofr-controlnet-preprocessors";

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: "f6584ef76cf07a2014ffe1e9bdb1a5cfa714f031883ab43f8d4b05506625988e", 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({
  hed: true,
  sam: true,
  mlsd: true,
  pidi: true,
  canny: true,
  image: "https://blog.api.market/wp-content/uploads/2026/10/flux-red-cinema-output-y3zss6rq-api-market.jpg",
  leres: true,
  midas: true,
  content: true,
  lineart: true,
  open_pose: true,
  normal_bae: true,
  face_detector: true,
  lineart_anime: true
}).then((output) => output.forEach((url) => console.log(url)));
```

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

API_KEY = "YOUR_API_MARKET_KEY"
BASE_URL = "https://prod.api.market/api/v1/magicapi/ai-image-preprocessing-fofr-controlnet-preprocessors"


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": "f6584ef76cf07a2014ffe1e9bdb1a5cfa714f031883ab43f8d4b05506625988e", "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")


output = create_and_wait_for_prediction({
    "hed": True,
    "sam": True,
    "mlsd": True,
    "pidi": True,
    "canny": True,
    "image": "https://blog.api.market/wp-content/uploads/2026/10/flux-red-cinema-output-y3zss6rq-api-market.jpg",
    "leres": True,
    "midas": True,
    "content": True,
    "lineart": True,
    "open_pose": True,
    "normal_bae": True,
    "face_detector": True,
    "lineart_anime": True,
})
for url in output:
    print(url)
```

## FAQ
- **How do I get only one map, such as depth?**
  - Set every other preprocessor field to `false` and leave the one you want (for example `midas`) as `true`. All of them default to `true`, so you have to switch off the ones you do not need.
- **How do I know which output is which?**
  - Each output file is named after its preprocessor, for example `canny.png` or `open_pose.png`.
- **Does turning preprocessors off lower the price?**
  - Only when a request would otherwise run past 59 seconds of processing. The example with all 13 preprocessors took 8.2 seconds, so it was 1 unit ($0.064).
- **Does this API generate new images?**
  - No. It only produces control maps from your image. Feed those maps to a ControlNet-capable image generator to create new images.
- **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. You can also email our support team at hello@magicapi.com.


Run 13 ControlNet preprocessors on one image with fofr ControlNet Preprocessors: canny, HED, MiDaS and LeReS depth, OpenPose, lineart, SAM and more.