Name: ControlNet Hough API: Line-Guided Image Generator
Brand: magicapi
SKU: api-magicapi-modify-images-with-line-detection-jagilley-controlnet-hough
Availability: InStock
Author: API Market

Shashank Agarwal

# 📐 Line-Guided Image Generator API (jagilley ControlNet Hough)

## Overview
ControlNet Hough, published by jagilley, generates a new image that follows the straight lines of an input image. It detects the lines with M-LSD (a straight line detector) and uses them to guide a Stable Diffusion image generated from your `prompt`.

Send an `image` and a `prompt`. The layout of walls, edges, furniture and other straight structures in the input is kept, while the content and style come from the prompt. This makes it a good fit for rooms, buildings and other scenes made of straight lines.

## Features
- **Structure from straight lines**: the M-LSD line map of the input image guides the new image.
- **Prompt control**: `prompt` describes the result; `a_prompt` (default "best quality, extremely detailed") is added to it and `n_prompt` lists what to avoid.
- **Line detection settings**: `detect_resolution` (128 to 1024, default 512), `value_threshold` (0.01 to 2, default 0.1) and `distance_threshold` (0.01 to 20, default 0.1).
- **Output size**: `image_resolution` of `256`, `512` (default) or `768`.
- **1 or 4 samples**: `num_samples` is `"1"` or `"4"` (sent as a string).
- **Sampling controls**: `ddim_steps` (default 20), `scale` (guidance scale, 0.1 to 30, default 9), `eta` (default 0) and `seed`.

## Use Cases
1. **Interior redesign**: keep the walls, windows and furniture layout of a room photo and change its style.
2. **Architecture concepts**: restyle building photos or sketches while keeping their lines.
3. **Product and set mockups**: generate variations of a scene with the same geometry.

## Visual Examples
### Example Input
Image:

![ControlNet Hough example input image](https://blog.api.market/wp-content/uploads/2026/10/controlnet-hough-input-api-market-1.png)

Prompt: "a cheerful modernist bedroom"

Settings: `scale` 9, `a_prompt` "best quality, extremely detailed", `n_prompt` "longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality", `ddim_steps` 20, `num_samples` "1", `value_threshold` 0.1, `image_resolution` "512", `detect_resolution` 512, `distance_threshold` 0.1.

### Example Output
The request returned two images: the detected line map and the generated bedroom.

![ControlNet Hough output 1: line map detected from the input image](https://blog.api.market/wp-content/uploads/2026/10/controlnet-hough-output-1-p79xkqsd-api-market.png)

![ControlNet Hough output 2: generated image for the cheerful modernist bedroom prompt](https://blog.api.market/wp-content/uploads/2026/10/controlnet-hough-output-2-p79xkqsd-api-market.png)

## Input Parameters
| Field | Type | Required | Default | Allowed values | Description |
| --- | --- | --- | --- | --- | --- |
| `image` | string (URL) | Yes |  |  | Input image URL (jpeg, png, gif or webp) |
| `prompt` | string | Yes |  |  | Prompt for the model |
| `num_samples` | string | No | `"1"` | `"1"`, `"4"` | Number of samples (higher values may run out of memory) |
| `image_resolution` | string | No | `"512"` | `"256"`, `"512"`, `"768"` | Image resolution to be generated |
| `ddim_steps` | integer | No | `20` |  | Steps |
| `scale` | number | No | `9` | 0.1 to 30 | Guidance scale |
| `seed` | integer | No | none |  | Seed |
| `eta` | number | No | `0` |  | eta (DDIM) |
| `a_prompt` | string | No | `best quality, extremely detailed` |  | Added prompt |
| `n_prompt` | string | No | `longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality` |  | Negative prompt |
| `detect_resolution` | integer | No | `512` | 128 to 1024 | Resolution used for line detection |
| `value_threshold` | number | No | `0.1` | 0.01 to 2 | Value threshold for M-LSD line detection |
| `distance_threshold` | number | No | `0.1` | 0.01 to 20 | Distance threshold for M-LSD line detection |

## Pricing
- **Pay As You Go (PAYG) pricing**: you only pay for what you use.
- **Price**: $0.014 per API unit.
- **1 API unit = 1 successful request with up to 9 seconds of processing.** A request that takes longer is billed one more unit for each started block of 9 seconds (for example, 12 seconds of processing is 2 units, $0.028).
- Four samples, a higher `image_resolution` or more `ddim_steps` take longer to process and can use more than one unit.
- **Example cost**: the example request above took 5.4 seconds of processing, so it used 1 API unit and cost $0.014.
- **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/modify-images-with-line-detection-jagilley-controlnet-hough`

### 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/modify-images-with-line-detection-jagilley-controlnet-hough/predictions" \
  -H "Content-Type: application/json" \
  -H "x-api-market-key: YOUR_API_MARKET_KEY" \
  -d '{
    "version": "854e8727697a057c525cdb45ab037f64ecca770a1769cc52287c2e56472a247b",
    "input": {
      "image": "https://blog.api.market/wp-content/uploads/2026/10/controlnet-hough-input-api-market-1.png",
      "scale": 9,
      "prompt": "a cheerful modernist bedroom",
      "a_prompt": "best quality, extremely detailed",
      "n_prompt": "longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality",
      "ddim_steps": 20,
      "num_samples": "1",
      "value_threshold": 0.1,
      "image_resolution": "512",
      "detect_resolution": 512,
      "distance_threshold": 0.1
    }
  }'
```

Response (201 Created):
```json
{
  "id": "p79xkqsdpsrne0d1ccs87f2f1r",
  "version": "854e8727697a057c525cdb45ab037f64ecca770a1769cc52287c2e56472a247b",
  "status": "starting",
  "created_at": "2026-10-22T10:39:55.492Z"
}
```

#### Check Prediction Status
```bash
curl -X GET "https://prod.api.market/api/v1/magicapi/modify-images-with-line-detection-jagilley-controlnet-hough/predictions/{id}" \
  -H "x-api-market-key: YOUR_API_MARKET_KEY"
```

Response when the prediction has finished (200 OK):
```json
{
  "id": "p79xkqsdpsrne0d1ccs87f2f1r",
  "status": "succeeded",
  "output": [
    "https://blog.api.market/wp-content/uploads/2026/10/controlnet-hough-output-1-p79xkqsd-api-market.png",
    "https://blog.api.market/wp-content/uploads/2026/10/controlnet-hough-output-2-p79xkqsd-api-market.png"
  ],
  "error": null,
  "created_at": "2026-10-22T10:39:55.492Z",
  "started_at": "2026-10-22T10:39:59.811Z",
  "completed_at": "2026-10-22T10:40:05.249Z"
}
```

`output` is a list of PNG image URLs. The first URL is the detected line map; the generated images follow it.

### 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 `prompt`, or `num_samples` sent as a number instead of the string `"1"` 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
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. Failed predictions are not billed.
- Make sure the `image` URL is publicly reachable.
- 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/modify-images-with-line-detection-jagilley-controlnet-hough";

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: "854e8727697a057c525cdb45ab037f64ecca770a1769cc52287c2e56472a247b", 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/2026/10/controlnet-hough-input-api-market-1.png",
  scale: 9,
  prompt: "a cheerful modernist bedroom",
  a_prompt: "best quality, extremely detailed",
  n_prompt: "longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality",
  ddim_steps: 20,
  num_samples: "1",
  value_threshold: 0.1,
  image_resolution: "512",
  detect_resolution: 512,
  distance_threshold: 0.1
}).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/modify-images-with-line-detection-jagilley-controlnet-hough"


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": "854e8727697a057c525cdb45ab037f64ecca770a1769cc52287c2e56472a247b", "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/2026/10/controlnet-hough-input-api-market-1.png",
    "scale": 9,
    "prompt": "a cheerful modernist bedroom",
    "a_prompt": "best quality, extremely detailed",
    "n_prompt": "longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality",
    "ddim_steps": 20,
    "num_samples": "1",
    "value_threshold": 0.1,
    "image_resolution": "512",
    "detect_resolution": 512,
    "distance_threshold": 0.1
}))
```

## FAQ
- **What kind of input image works best?**
  - Images with clear straight lines, such as rooms, buildings and furniture. The model follows the straight lines it detects, so organic shapes give it little to work with.
- **Why does the output contain one more image than I asked for?**
  - The first URL is the line map detected from your input image. The generated images follow it.
- **Why are `num_samples` and `image_resolution` strings?**
  - The model accepts them as strings: `num_samples` is `"1"` or `"4"` and `image_resolution` is `"256"`, `"512"` or `"768"`.
- **How do I get more or fewer lines detected?**
  - Adjust `value_threshold` and `distance_threshold`, and `detect_resolution` for the size the detector works at.
- **How is a request billed?**
  - $0.014 per request for up to 9 seconds of processing, plus one more unit for each further started block of 9 seconds. The example took 5.4 seconds and cost $0.014.
- **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`.

## 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.


Restyle rooms, buildings and other straight-line scenes: ControlNet Hough detects lines with M-LSD and generates a new image from your prompt.