Name: ControlNet Lineart API: Line Art to Realistic Images
Brand: magicapi
SKU: api-magicapi-lineart-realistic-vision-api-usamaehsan-controlnet-1-1-x-realistic-vision-v2-0
Availability: InStock
Author: API Market

Shashank Agarwal

# 📷 Line Art to Realistic Image API (usamaehsan ControlNet 1.1 x Realistic Vision v2.0)

## Overview
This model, published by usamaehsan, combines the ControlNet 1.1 lineart model with the Realistic Vision photorealistic Stable Diffusion model (its developer lists Realistic Vision v2.0, updated to v5). It generates a realistic image that follows the lines of your input image.

Send an `image` and a `prompt`. The outlines and composition of the input guide the result, while the prompt sets the subject, materials and mood. The API returns the URL of one image.

## Features
- **Line-guided generation**: the line structure of the input `image` controls the composition of the new image.
- **Photorealistic style**: the default `negative_prompt` steers away from cartoon, CGI, 3D render, sketch and anime looks.
- **Control strength**: `strength` from 0 to 2 (default 0.8) sets how closely the result follows the lines.
- **Size limits**: `max_width` and `max_height` (minimum 128, default 612) cap the size of the image the model works on.
- **Sampling controls**: `steps` from 0 to 100 (default 20), `guidance_scale` from 0 to 30 (default 10) and `seed`.

## Use Cases
1. **Sketch to photo**: turn line drawings and outlines into realistic images.
2. **Restyling photos**: keep the composition of a photo and change the scene with a new prompt.
3. **Concept visualization**: try several realistic versions of the same layout for products, rooms or scenes.

## Visual Examples
### Example Input
Image:

![ControlNet 1.1 x Realistic Vision example input image](https://blog.api.market/wp-content/uploads/2026/10/controlnet-1-1-x-realistic-vision-v2-0-input-api-market.jpg)

Prompt: "underwater kingdom"

Settings: `steps` 20, `strength` 0.5, `max_width` 612, `max_height` 612, `guidance_scale` 10, and the model's default `negative_prompt`.

### Example Output
![ControlNet 1.1 x Realistic Vision output generated from the underwater kingdom example prompt](https://blog.api.market/wp-content/uploads/2026/10/controlnet-1-1-x-realistic-vision-v2-0-output-0pcvx2c8-api-market-1.png)

## Input Parameters
| Field | Type | Required | Default | Allowed values | Description |
| --- | --- | --- | --- | --- | --- |
| `image` | string (URL) | Yes |  |  | Input image URL (jpeg, png, gif or webp) |
| `prompt` | string | No | `(a tabby cat)+++, high resolution, sitting on a park bench` |  | What to generate |
| `negative_prompt` | string | No | `(deformed iris, deformed pupils, semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime:1.4), text, close up, cropped, out of frame, worst quality, low quality, jpeg artifacts, ugly, duplicate, morbid, mutilated, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, mutation, deformed, blurry, dehydrated, bad anatomy, bad proportions, extra limbs, cloned face, disfigured, gross proportions, malformed limbs, missing arms, missing legs, extra arms, extra legs, fused fingers, too many fingers, long neck` |  | What to avoid in the image |
| `strength` | number | No | `0.8` | 0 to 2 | Control strength/weight |
| `max_height` | number | No | `612` | minimum 128 | Max height of mask/image |
| `max_width` | number | No | `612` | minimum 128 | Max width of mask/image |
| `steps` | integer | No | `20` | 0 to 100 | Number of inference steps |
| `seed` | integer | No | none |  | Leave blank to randomize |
| `guidance_scale` | integer | No | `10` | 0 to 30 | Guidance scale |

## Pricing
- **Pay As You Go (PAYG) pricing**: you only pay for what you use.
- **Price**: $0.058 per API unit.
- **1 API unit = 1 successful request with up to 37 seconds of processing.** A request that takes longer is billed one more unit for each started block of 37 seconds (for example, 40 seconds of processing is 2 units, $0.116).
- Each request returns one image.
- **Example cost**: the example request above took 3.7 seconds of processing, so it used 1 API unit and cost $0.058.
- **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/lineart-realistic-vision-api-usamaehsan-controlnet-1-1-x-realistic-vision-v2-0`

### 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/lineart-realistic-vision-api-usamaehsan-controlnet-1-1-x-realistic-vision-v2-0/predictions" \
  -H "Content-Type: application/json" \
  -H "x-api-market-key: YOUR_API_MARKET_KEY" \
  -d '{
    "version": "51778c7522eb99added82c0c52873d7a391eecf5fcc3ac7856613b7e6443f2f7",
    "input": {
      "image": "https://blog.api.market/wp-content/uploads/2026/10/controlnet-1-1-x-realistic-vision-v2-0-input-api-market.jpg",
      "steps": 20,
      "prompt": "underwater kingdom",
      "strength": 0.5,
      "max_width": 612,
      "max_height": 612,
      "guidance_scale": 10,
      "negative_prompt": "(deformed iris, deformed pupils, semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime:1.4), text, close up, cropped, out of frame, worst quality, low quality, jpeg artifacts, ugly, duplicate, morbid, mutilated, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, mutation, deformed, blurry, dehydrated, bad anatomy, bad proportions, extra limbs, cloned face, disfigured, gross proportions, malformed limbs, missing arms, missing legs, extra arms, extra legs, fused fingers, too many fingers, long neck"
    }
  }'
```

Response (201 Created):
```json
{
  "id": "0pcvx2c8g1rne0d1ccyrw0bw2m",
  "version": "51778c7522eb99added82c0c52873d7a391eecf5fcc3ac7856613b7e6443f2f7",
  "status": "starting",
  "created_at": "2026-10-22T10:52:19.735Z"
}
```

#### Check Prediction Status
```bash
curl -X GET "https://prod.api.market/api/v1/magicapi/lineart-realistic-vision-api-usamaehsan-controlnet-1-1-x-realistic-vision-v2-0/predictions/{id}" \
  -H "x-api-market-key: YOUR_API_MARKET_KEY"
```

Response when the prediction has finished (200 OK):
```json
{
  "id": "0pcvx2c8g1rne0d1ccyrw0bw2m",
  "status": "succeeded",
  "output": "https://blog.api.market/wp-content/uploads/2026/10/controlnet-1-1-x-realistic-vision-v2-0-output-0pcvx2c8-api-market-1.png",
  "error": null,
  "created_at": "2026-10-22T10:52:19.735Z",
  "started_at": "2026-10-22T10:52:57.756Z",
  "completed_at": "2026-10-22T10:53:01.429Z"
}
```

`output` is a single URL string pointing to the generated PNG 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 `strength` above 2.
- **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/lineart-realistic-vision-api-usamaehsan-controlnet-1-1-x-realistic-vision-v2-0";

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: "51778c7522eb99added82c0c52873d7a391eecf5fcc3ac7856613b7e6443f2f7", 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-1-1-x-realistic-vision-v2-0-input-api-market.jpg",
  steps: 20,
  prompt: "underwater kingdom",
  strength: 0.5,
  max_width: 612,
  max_height: 612,
  guidance_scale: 10,
  negative_prompt: "(deformed iris, deformed pupils, semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime:1.4), text, close up, cropped, out of frame, worst quality, low quality, jpeg artifacts, ugly, duplicate, morbid, mutilated, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, mutation, deformed, blurry, dehydrated, bad anatomy, bad proportions, extra limbs, cloned face, disfigured, gross proportions, malformed limbs, missing arms, missing legs, extra arms, extra legs, fused fingers, too many fingers, long neck"
}).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/lineart-realistic-vision-api-usamaehsan-controlnet-1-1-x-realistic-vision-v2-0"


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": "51778c7522eb99added82c0c52873d7a391eecf5fcc3ac7856613b7e6443f2f7", "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-1-1-x-realistic-vision-v2-0-input-api-market.jpg",
    "steps": 20,
    "prompt": "underwater kingdom",
    "strength": 0.5,
    "max_width": 612,
    "max_height": 612,
    "guidance_scale": 10,
    "negative_prompt": "(deformed iris, deformed pupils, semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime:1.4), text, close up, cropped, out of frame, worst quality, low quality, jpeg artifacts, ugly, duplicate, morbid, mutilated, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, mutation, deformed, blurry, dehydrated, bad anatomy, bad proportions, extra limbs, cloned face, disfigured, gross proportions, malformed limbs, missing arms, missing legs, extra arms, extra legs, fused fingers, too many fingers, long neck"
}))
```

## FAQ
- **What does `strength` do?**
  - It sets how strongly the lines of the input image control the result, from 0 to 2 (default 0.8). Lower values give the prompt more freedom; the example used 0.5.
- **How large is the output image?**
  - The model works within `max_width` and `max_height` (default 612 each, minimum 128). Raise them for a larger image.
- **Do I have to send a prompt?**
  - Only `image` is required. Without a `prompt` the model uses its default, "(a tabby cat)+++, high resolution, sitting on a park bench", so send your own prompt for real use.
- **How many images does one request return?**
  - One. `output` is a single image URL.
- **How is a request billed?**
  - $0.058 per request for up to 37 seconds of processing, plus one more unit for each further started block of 37 seconds. The example took 3.7 seconds and cost $0.058.
- **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.


Turn line art, sketches or photos into realistic images that keep their composition, with ControlNet 1.1 lineart and Realistic Vision.