Name: ControlNet Seg API: Segmentation-Guided Image Generator
Brand: magicapi
SKU: api-magicapi-semantic-segmentation-image-modifier-jagilley-controlnet-seg
Availability: InStock
Author: API Market

Shashank Agarwal

# 🎨 Segmentation Guided Image Generator API (jagilley ControlNet Seg)

## Overview
ControlNet Seg generates new images that keep the layout of an input image. The model detects a semantic segmentation map (which regions are building, sky, grass and so on) from your `image` and uses it, together with your text `prompt`, to guide a new image.

Send an image URL and a prompt. The result is a list of image URLs: the detected segmentation map followed by the generated image or images.

## Features
- **Layout-guided generation**: the segmentation map detected from your image keeps where each region sits in the scene.
- **Text control**: `prompt` sets the content and style; `a_prompt` is added to every prompt and `n_prompt` lists things to avoid.
- **One or four samples**: set `num_samples` to `"1"` or `"4"`.
- **Output resolution**: `image_resolution` of `"256"`, `"512"` (default) or `"768"`.
- **Detection resolution**: `detect_resolution` (128 to 1024) sets the resolution used for segmentation.
- **Sampling control**: `ddim_steps`, `scale` (0.1 to 30), `eta` and `seed`.

## Use Cases
1. **Architecture and interiors**: keep the layout of a building or room and change its style with a prompt.
2. **Scene variations**: produce several versions of the same scene with `num_samples` set to `"4"`.
3. **Concept art**: turn a reference photo into a new scene with the same composition.
4. **Segmentation maps**: the detected segmentation map is returned too, so you can reuse it in other tools.

## Visual Examples
### Example Input
The example sends a photo of a house with the prompt "A modernist house in a nice landscape" and keeps the default settings.

![Input image for ControlNet Seg: a house photo](https://blog.api.market/wp-content/uploads/2026/10/controlnet-seg-input-api-market.png)

```json
{
  "image": "https://blog.api.market/wp-content/uploads/2026/10/controlnet-seg-input-api-market.png",
  "scale": 9,
  "prompt": "A modernist house in a nice landscape",
  "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",
  "image_resolution": "512",
  "detect_resolution": 512
}
```

### Example Output
The request returned two images: the detected segmentation map and the generated image.

![ControlNet Seg output 1: segmentation map detected from the input image](https://blog.api.market/wp-content/uploads/2026/10/controlnet-seg-output-1-r0k8xe42-api-market.png)

![ControlNet Seg output 2: generated modernist house in a landscape](https://blog.api.market/wp-content/uploads/2026/10/controlnet-seg-output-2-r0k8xe42-api-market.png)

## Input Parameters
| Field | Type | Required | Default | Allowed values | Description |
| --- | --- | --- | --- | --- | --- |
| `image` | string (URL) | Yes | none |  | Input image URL (jpeg, png, gif or webp). The segmentation map is detected from this image. |
| `prompt` | string | Yes | none |  | Text description of the image to generate. |
| `num_samples` | string | No | `"1"` | `"1"`, `"4"` | Number of images to generate, sent as a string. Higher values use more memory. |
| `image_resolution` | string | No | `"512"` | `"256"`, `"512"`, `"768"` | Resolution of the generated image in pixels, sent as a string. |
| `ddim_steps` | integer | No | `20` |  | Number of DDIM sampling steps. |
| `scale` | number | No | `9` | 0.1 to 30 | Guidance scale: how closely the result follows the prompt. |
| `seed` | integer | No | none |  | Seed for reproducible results. Random when omitted. |
| `eta` | number | No | `0` |  | DDIM eta value. |
| `a_prompt` | string | No | `best quality, extremely detailed` |  | Text added 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: things to avoid in the result. |
| `detect_resolution` | integer | No | `512` | 128 to 1024 | Resolution used for segmentation detection. |

## Pricing
- **Pay As You Go (PAYG) pricing**: you only pay for what you use.
- **Price**: $0.011 per API unit.
- **1 API unit = 1 successful request** that uses up to 7 seconds of processing time. A request that needs more processing time is billed one more unit for each started block of 7 seconds (for example, 8 to 14 seconds of processing is 2 units, $0.022).
- Larger `num_samples` and `image_resolution` values take longer to process; a request that runs past 7 seconds of processing uses more than one unit.
- **Example cost**: the example request on this page used 4.5 seconds of processing, so it was billed 1 unit ($0.011).
- **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/semantic-segmentation-image-modifier-jagilley-controlnet-seg`

### 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/semantic-segmentation-image-modifier-jagilley-controlnet-seg/predictions" \
  -H "Content-Type: application/json" \
  -H "x-api-market-key: YOUR_API_MARKET_KEY" \
  -d '{
    "version": "f967b165f4cd2e151d11e7450a8214e5d22ad2007f042f2f891ca3981dbfba0d",
    "input": {
      "image": "https://blog.api.market/wp-content/uploads/2026/10/controlnet-seg-input-api-market.png",
      "scale": 9,
      "prompt": "A modernist house in a nice landscape",
      "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",
      "image_resolution": "512",
      "detect_resolution": 512
    }
  }'
```

Response (201 Created):
```json
{
  "id": "r0k8xe42v1rna0d1d10s5km4hc",
  "version": "f967b165f4cd2e151d11e7450a8214e5d22ad2007f042f2f891ca3981dbfba0d",
  "status": "starting",
  "created_at": "2026-10-23T10:14:46.430Z"
}
```

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

Response when the prediction has finished (200 OK):
```json
{
  "id": "r0k8xe42v1rna0d1d10s5km4hc",
  "status": "succeeded",
  "output": [
    "https://blog.api.market/wp-content/uploads/2026/10/controlnet-seg-output-1-r0k8xe42-api-market.png",
    "https://blog.api.market/wp-content/uploads/2026/10/controlnet-seg-output-2-r0k8xe42-api-market.png"
  ],
  "error": null,
  "created_at": "2026-10-23T10:14:46.430Z",
  "started_at": "2026-10-23T10:16:41.089Z",
  "completed_at": "2026-10-23T10:16:45.557Z"
}
```

`output` is a list of image URLs. The first URL is the segmentation map detected from your input image, followed by the generated images (`num_samples` of them).

### 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/semantic-segmentation-image-modifier-jagilley-controlnet-seg";

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: "f967b165f4cd2e151d11e7450a8214e5d22ad2007f042f2f891ca3981dbfba0d", 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-seg-input-api-market.png",
    "scale": 9,
    "prompt": "A modernist house in a nice landscape",
    "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",
    "image_resolution": "512",
    "detect_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/semantic-segmentation-image-modifier-jagilley-controlnet-seg"


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": "f967b165f4cd2e151d11e7450a8214e5d22ad2007f042f2f891ca3981dbfba0d", "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-seg-input-api-market.png",
    "scale": 9,
    "prompt": "A modernist house in a nice landscape",
    "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",
    "image_resolution": "512",
    "detect_resolution": 512
}))
```

## FAQ
- **Why does the output contain one more image than I asked for?**
  - The first image in `output` is the segmentation map detected from your input. The generated images follow it.
- **Are `num_samples` and `image_resolution` numbers?**
  - No. Both are strings with fixed values: `num_samples` is `"1"` or `"4"`, `image_resolution` is `"256"`, `"512"` or `"768"`.
- **Can one request cost more than one unit?**
  - Yes. One unit covers up to 7 seconds of processing. The example took 4.5 seconds; four samples at `"768"` take longer and can use 2 or more units.
- **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, 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.


Generate images that follow the segmentation map of an input photo with jagilley's ControlNet Seg and a text prompt. $0.011 per API unit, pay as you go.