Name: ControlNet Canny API: Edge-Guided Image Generation
Brand: magicapi
SKU: api-magicapi-image-modification-canny-edge-detection-jagilley-controlnet-canny
Availability: InStock
Author: API Market

Shashank Agarwal

# ✏️ Edge-Guided Image Generation API (jagilley ControlNet Canny)

## Overview
ControlNet Canny, published by jagilley, modifies images using Canny edge detection. It detects the edges in the input `image` and generates a new image that keeps that outline while following your text `prompt`.

Each request returns a list of image URLs. In the example, with `num_samples` set to `"1"`, the list held two images: the detected edge map first, then the generated image.

## Features
- **Edge-guided generation**: the composition and outlines come from the input image; the content and style come from `prompt`.
- **Edge sensitivity**: `low_threshold` (default 100) and `high_threshold` (default 200), each from 1 to 255, control which edges the Canny detector keeps.
- **Samples**: `num_samples` is the string `"1"` (default) or `"4"`. The field description warns that higher values may run out of memory.
- **Resolution**: `image_resolution` is `"256"`, `"512"` (default) or `"768"`.
- **Prompt helpers**: `a_prompt` is appended to your prompt (default `best quality, extremely detailed`) and `n_prompt` is the negative prompt, with a default list of common defects.
- **Sampling controls**: `ddim_steps` (default 20), `scale` for guidance (0.1 to 30, default 9), `eta` for added noise (default 0) and `seed`.

## Use Cases
1. **Restyling photos**: keep a photo's composition and change its subject or style, such as turning a bird into a metallic cyborg bird.
2. **Line art to images**: render sketches or line drawings into finished images that follow the lines.
3. **Product concepts**: try different materials and finishes on the same product outline.
4. **Interior and architecture variations**: keep a room's or building's structure and change its look.

## Visual Examples
### Example Input
Prompt: "a metallic cyborg bird"

![Example input image: a bird](https://blog.api.market/wp-content/uploads/2026/10/controlnet-canny-input-api-market-1.jpeg)

The other fields were sent at their default values (one sample at 512 resolution, thresholds 100 and 200).

```json
{
  "image": "https://blog.api.market/wp-content/uploads/2026/10/controlnet-canny-input-api-market-1.jpeg",
  "scale": 9,
  "prompt": "a metallic cyborg bird",
  "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",
  "low_threshold": 100,
  "high_threshold": 200,
  "image_resolution": "512"
}
```

### Example Output
The request returned two images.

![ControlNet Canny output 1: the Canny edge map detected from the input image](https://blog.api.market/wp-content/uploads/2026/10/controlnet-canny-output-1-mw27s0ss-api-market.png)

![ControlNet Canny output 2: the generated metallic cyborg bird following the input's edges](https://blog.api.market/wp-content/uploads/2026/10/controlnet-canny-output-2-mw27s0ss-api-market.png)

## Input Parameters
| Field | Type | Required | Default | Allowed values | Description |
| --- | --- | --- | --- | --- | --- |
| `image` | string (URL) | Yes |  |  | URL of the input image |
| `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 |
| `low_threshold` | integer | No | `100` | 1 to 255 | Canny line detection low threshold |
| `high_threshold` | integer | No | `200` | 1 to 255 | Canny line detection high threshold |
| `ddim_steps` | integer | No | `20` |  | Number of denoising steps |
| `scale` | number | No | `9` | 0.1 to 30 | Scale for classifier-free guidance |
| `seed` | integer | No | none |  | Random seed. Leave blank for a random result |
| `eta` | number | No | `0` |  | Controls the amount of noise added during the denoising process. Higher values add more noise |
| `a_prompt` | string | No | `best quality, extremely detailed` |  | Additional text appended to the prompt |
| `n_prompt` | string | No | `longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality` |  | Negative prompt |

## Pricing
- **Pay As You Go (PAYG) pricing**: you only pay for what you use.
- **Price**: $0.078 per API unit.
- **1 API unit = 1 request with up to 50 seconds of processing.** A longer request uses one more unit per started 50-second block (for example, 51 seconds of processing uses 2 units, $0.156).
- `num_samples` `"4"` takes longer than `"1"`, so it can use more units if processing passes 50 seconds.
- **Example cost**: the example took 6.35 seconds of processing, which is 1 unit, $0.078.
- **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-modification-canny-edge-detection-jagilley-controlnet-canny`

### 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/image-modification-canny-edge-detection-jagilley-controlnet-canny/predictions" \
  -H "Content-Type: application/json" \
  -H "x-api-market-key: YOUR_API_MARKET_KEY" \
  -d '{
    "version": "aff48af9c68d162388d230a2ab003f68d2638d88307bdaf1c2f1ac95079c9613",
    "input": {
      "image": "https://blog.api.market/wp-content/uploads/2026/10/controlnet-canny-input-api-market-1.jpeg",
      "scale": 9,
      "prompt": "a metallic cyborg bird",
      "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",
      "low_threshold": 100,
      "high_threshold": 200,
      "image_resolution": "512"
    }
  }'
```

Response (201 Created):
```json
{
  "id": "mw27s0ssaxrne0d1ccrbbt2cvw",
  "version": "aff48af9c68d162388d230a2ab003f68d2638d88307bdaf1c2f1ac95079c9613",
  "status": "starting",
  "created_at": "2026-10-22T10:37:47.425Z"
}
```

#### Check Prediction Status
```bash
curl -X GET "https://prod.api.market/api/v1/magicapi/image-modification-canny-edge-detection-jagilley-controlnet-canny/predictions/{id}" \
  -H "x-api-market-key: YOUR_API_MARKET_KEY"
```

Response when the prediction has finished (200 OK):
```json
{
  "id": "mw27s0ssaxrne0d1ccrbbt2cvw",
  "status": "succeeded",
  "output": [
    "https://blog.api.market/wp-content/uploads/2026/10/controlnet-canny-output-1-mw27s0ss-api-market.png",
    "https://blog.api.market/wp-content/uploads/2026/10/controlnet-canny-output-2-mw27s0ss-api-market.png"
  ],
  "error": null,
  "created_at": "2026-10-22T10:37:47.425Z",
  "started_at": "2026-10-22T10:38:32.694Z",
  "completed_at": "2026-10-22T10:38:40.046Z"
}
```

`output` is a list of image URLs. In the example, the first URL is the detected edge map and the second is the generated 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 `prompt`, or a `num_samples` value other than `"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.
- 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-modification-canny-edge-detection-jagilley-controlnet-canny";

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: "aff48af9c68d162388d230a2ab003f68d2638d88307bdaf1c2f1ac95079c9613", 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-canny-input-api-market-1.jpeg",
  "scale": 9,
  "prompt": "a metallic cyborg bird",
  "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",
  "low_threshold": 100,
  "high_threshold": 200,
  "image_resolution": "512"
}).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-modification-canny-edge-detection-jagilley-controlnet-canny"


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": "aff48af9c68d162388d230a2ab003f68d2638d88307bdaf1c2f1ac95079c9613", "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({
    "image": "https://blog.api.market/wp-content/uploads/2026/10/controlnet-canny-input-api-market-1.jpeg",
    "scale": 9,
    "prompt": "a metallic cyborg bird",
    "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",
    "low_threshold": 100,
    "high_threshold": 200,
    "image_resolution": "512"
})
print(output)
```

## FAQ
- **Why did one sample return two images?**
  - The list starts with the Canny edge map detected from your input, followed by the generated sample. In the example, `num_samples` `"1"` returned two URLs.
- **How do I keep more or fewer edges?**
  - Lower `low_threshold` and `high_threshold` to keep fainter edges, or raise them to keep only strong outlines. Both range from 1 to 255.
- **Why are `num_samples` and `image_resolution` strings?**
  - They are enumerations in the model's schema. Send `"1"` or `"4"` and `"256"`, `"512"` or `"768"` as strings, not numbers.
- **Do I need to write a negative prompt?**
  - No. `n_prompt` has a default list of common defects such as low quality and bad hands. Send your own value to replace it.
- **Does generating 4 samples cost more?**
  - Billing is by processing time. One unit covers up to 50 seconds; the example with one sample took 6.35 seconds.
- **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.


Modify images with ControlNet Canny: detect the edges of an input image and generate a new image from a text prompt that keeps the outline.