Name: RealVisXL V3.0 Turbo API: Photorealistic Image Generator
Brand: magicapi
SKU: api-magicapi-photorealistic-image-generation-adirik-realvisxl-v3-0-turbo
Availability: InStock
Author: API Market

Shashank Agarwal

# 📸 Photorealistic Image Generator API (adirik RealVisXL V3.0 Turbo)

## Overview
RealVisXL V3.0 Turbo is a photorealistic image model based on SDXL, packaged by adirik. Its developer describes it as focused on photorealism.

Send a text `prompt` to generate images. Add an `image` to run image-to-image, or an `image` plus a `mask` to inpaint part of a picture. Each request returns a list of 1 to 4 image URLs (`num_outputs`).

## Features
- **Text-to-image**: generate images from a `prompt`, with a default `negative_prompt` that steers away from illustration and low-quality styles.
- **Image-to-image**: pass an `image` and set `prompt_strength` (0 to 1) to control how much of the original is replaced.
- **Inpainting**: pass an `image` and a `mask`. Black mask areas are preserved, white areas are regenerated.
- **Up to 4 images per request**: set `num_outputs` from 1 to 4.
- **Size control**: set `width` and `height` in pixels (default 768 x 768).
- **Sampling control**: choose one of 8 schedulers, the number of denoising steps (1 to 500) and the guidance scale (1 to 50).
- **Refiner options**: `no_refiner` (default), `expert_ensemble_refiner` or `base_image_refiner`.
- **Seed**: set `seed` to reproduce a result.

## Use Cases
1. **Photorealistic stock-style images**: people, places and products described in a prompt.
2. **Concept variations**: generate up to 4 candidates per request and pick the best.
3. **Photo edits**: regenerate a masked region of an existing photo with inpainting.
4. **Restyling a photo**: run image-to-image with a new prompt and a moderate `prompt_strength`.

## Visual Examples
### Example Input
```json
{
  "width": 768,
  "height": 768,
  "prompt": "An astronaut riding a rainbow unicorn",
  "refine": "no_refiner",
  "scheduler": "DPM++_SDE_Karras",
  "num_outputs": 1,
  "guidance_scale": 2,
  "apply_watermark": false,
  "high_noise_frac": 0.8,
  "negative_prompt": "(worst quality, low quality, illustration, 3d, 2d, painting, cartoons, sketch), open mouth",
  "prompt_strength": 0.8,
  "num_inference_steps": 25
}
```

### Example Output
![RealVisXL V3.0 Turbo output for the prompt An astronaut riding a rainbow unicorn](https://blog.api.market/wp-content/uploads/2026/10/realvisxl-v3-0-turbo-output-twzfebzp-api-market.png)

## Input Parameters
| Field | Type | Required | Default | Allowed values | Description |
| --- | --- | --- | --- | --- | --- |
| `prompt` | string | No | `An astronaut riding a rainbow unicorn` |  | Input prompt |
| `negative_prompt` | string | No | `(worst quality, low quality, illustration, 3d, 2d, painting, cartoons, sketch), open mouth` |  | Things to avoid in the image |
| `image` | string (URL) | No | none |  | Input image for img2img or inpaint mode |
| `mask` | string (URL) | No | none |  | Input mask for inpaint mode. Black areas will be preserved, white areas will be inpainted. |
| `width` | integer | No | `768` |  | Width of output image |
| `height` | integer | No | `768` |  | Height of output image |
| `num_outputs` | integer | No | `1` | 1 to 4 | Number of images to output |
| `scheduler` | string | No | `DPM++_SDE_Karras` | `DDIM`, `DPMSolverMultistep`, `HeunDiscrete`, `KarrasDPM`, `K_EULER_ANCESTRAL`, `K_EULER`, `PNDM`, `DPM++_SDE_Karras` | Scheduler to use. DPM++ SDE Karras is recommended. |
| `num_inference_steps` | integer | No | `25` | 1 to 500 | Number of denoising steps |
| `guidance_scale` | number | No | `2` | 1 to 50 | Scale for classifier-free guidance |
| `prompt_strength` | number | No | `0.8` | 0 to 1 | Prompt strength when using img2img or inpaint. 1.0 corresponds to full destruction of information in the image. |
| `seed` | integer | No | none |  | Random seed. Leave blank to randomize the seed. |
| `refine` | string | No | `no_refiner` | `no_refiner`, `expert_ensemble_refiner`, `base_image_refiner` | Which refine style to use |
| `high_noise_frac` | number | No | `0.8` | 0 to 1 | For `expert_ensemble_refiner`, the fraction of noise to use |
| `refine_steps` | integer | No | none |  | For `base_image_refiner`, the number of steps to refine. Defaults to `num_inference_steps`. |
| `apply_watermark` | boolean | No | `false` |  | Applies a watermark to enable determining if an image is generated in downstream applications |
| `disable_safety_checker` | boolean | No | `false` |  | Disable the safety checker for generated images |

## Pricing
- **Pay As You Go (PAYG) pricing**: you only pay for what you use.
- **Price**: $0.011 per API unit.
- **1 API unit = 1 request covering up to 10 seconds of processing.** A request that processes for longer uses one unit per started 10-second block (for example 11 seconds = 2 units, $0.022). More outputs, more steps and larger sizes take longer.
- **Example cost**: the example request processed for 2.79 seconds = 1 API 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/photorealistic-image-generation-adirik-realvisxl-v3-0-turbo`

### 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/photorealistic-image-generation-adirik-realvisxl-v3-0-turbo/predictions" \
  -H "Content-Type: application/json" \
  -H "x-api-market-key: YOUR_API_MARKET_KEY" \
  -d '{
    "version": "3dc73c805b11b4b01a60555e532fd3ab3f0e60d26f6584d9b8ba7e1b95858243",
    "input": {
      "width": 768,
      "height": 768,
      "prompt": "An astronaut riding a rainbow unicorn",
      "refine": "no_refiner",
      "scheduler": "DPM++_SDE_Karras",
      "num_outputs": 1,
      "guidance_scale": 2,
      "apply_watermark": false,
      "high_noise_frac": 0.8,
      "negative_prompt": "(worst quality, low quality, illustration, 3d, 2d, painting, cartoons, sketch), open mouth",
      "prompt_strength": 0.8,
      "num_inference_steps": 25
    }
  }'
```

Response (201 Created):
```json
{
  "id": "twzfebzp4hrmt0d1cch9gmk1g0",
  "version": "3dc73c805b11b4b01a60555e532fd3ab3f0e60d26f6584d9b8ba7e1b95858243",
  "status": "starting",
  "created_at": "2026-10-22T10:23:18.202Z"
}
```

#### Check Prediction Status
```bash
curl -X GET "https://prod.api.market/api/v1/magicapi/photorealistic-image-generation-adirik-realvisxl-v3-0-turbo/predictions/{id}" \
  -H "x-api-market-key: YOUR_API_MARKET_KEY"
```

Response when the prediction has finished (200 OK):
```json
{
  "id": "twzfebzp4hrmt0d1cch9gmk1g0",
  "status": "succeeded",
  "output": [
    "https://blog.api.market/wp-content/uploads/2026/10/realvisxl-v3-0-turbo-output-twzfebzp-api-market.png"
  ],
  "error": null,
  "created_at": "2026-10-22T10:23:18.202Z",
  "started_at": "2026-10-22T10:24:27.718Z",
  "completed_at": "2026-10-22T10:24:30.503Z"
}
```

`output` is a list of image URLs, one per requested output (`num_outputs`).

### 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 `num_outputs` above 4 or a `scheduler` that is not in the list.
- **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/photorealistic-image-generation-adirik-realvisxl-v3-0-turbo";

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: "3dc73c805b11b4b01a60555e532fd3ab3f0e60d26f6584d9b8ba7e1b95858243", 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({
  width: 768,
  height: 768,
  prompt: "An astronaut riding a rainbow unicorn",
  refine: "no_refiner",
  scheduler: "DPM++_SDE_Karras",
  num_outputs: 1,
  guidance_scale: 2,
  apply_watermark: false,
  high_noise_frac: 0.8,
  negative_prompt: "(worst quality, low quality, illustration, 3d, 2d, painting, cartoons, sketch), open mouth",
  prompt_strength: 0.8,
  num_inference_steps: 25
}).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/photorealistic-image-generation-adirik-realvisxl-v3-0-turbo"


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": "3dc73c805b11b4b01a60555e532fd3ab3f0e60d26f6584d9b8ba7e1b95858243", "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({
    "width": 768,
    "height": 768,
    "prompt": "An astronaut riding a rainbow unicorn",
    "refine": "no_refiner",
    "scheduler": "DPM++_SDE_Karras",
    "num_outputs": 1,
    "guidance_scale": 2,
    "apply_watermark": False,
    "high_noise_frac": 0.8,
    "negative_prompt": "(worst quality, low quality, illustration, 3d, 2d, painting, cartoons, sketch), open mouth",
    "prompt_strength": 0.8,
    "num_inference_steps": 25
}))
```

## FAQ
- **How many images does one request return?**
  - Between 1 and 4, set by `num_outputs` (default 1). The price is based on processing time, so more images can take more than one API unit.
- **How do I edit part of an existing photo?**
  - Send the photo as `image` and a black and white `mask` of the same picture. White areas are regenerated from the `prompt`, black areas are kept.
- **What does `prompt_strength` do?**
  - In image-to-image and inpaint mode it sets how much the input image is changed. 1.0 replaces all of its information; lower values keep more of the original.
- **Why is the default guidance scale so low?**
  - The Turbo model's default `guidance_scale` is 2 and the default step count is 25. You can raise both (guidance up to 50, steps up to 500), which also increases processing time.
- **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.


Generate up to 4 photorealistic images per request with RealVisXL V3.0 Turbo, with image-to-image and inpainting. Pay as you go, no monthly fee.