Name: Baidu ERNIE-Image Text-to-Image Generator API
Brand: magicapi
SKU: api-magicapi-text-to-image-generator-prunaai-ernie-image
Availability: InStock
Author: API Market

Shashank Agarwal

# 🎨 Text-to-Image Generator API (Baidu ERNIE-Image)

## Overview
ERNIE-Image generates images from a text prompt. Its developer describes it as an open text-to-image generation model built by the ERNIE-Image team at Baidu; this listing runs a version published by Pruna AI.

Send a `prompt` and the API returns a list of 1 to 4 image URLs. You can set the size (`width` and `height`, 64 to 2048 pixels), the number of steps and the guidance scale, turn the built-in prompt enhancer on or off, fix a `seed` and choose the output format.

## Features
- **Text to image**: describe the scene in `prompt` and get images back.
- **Custom size**: `width` and `height` from 64 to 2048 pixels (default 1024 x 1024). The model card's recommended sizes give the best results.
- **Prompt enhancer**: `use_pe` (default `true`) runs the prompt enhancer recommended by the model card before generation.
- **Quality controls**: `num_inference_steps` 1 to 100 (default 50) and `guidance_scale` 0 to 20 (default 4).
- **1 to 4 images per request**: set `num_outputs`.
- **Output formats**: `jpg` (default), `png` or `webp`, with `output_quality` 0 to 100.

## Use Cases
1. **Blog and article images**: create a header image from a one-line description.
2. **Concept art and mood boards**: try several takes on a scene with `num_outputs` up to 4.
3. **Marketing visuals**: generate backgrounds and scenes for campaigns.
4. **App features**: add text-to-image generation to a design or content tool.

## Visual Examples
### Example Input
Prompt: "a beautiful landscape"

Settings: `width` `1024`, `height` `1024`, `use_pe` `true`, `num_inference_steps` `50`, `guidance_scale` `4`, `num_outputs` `1`, `output_format` `jpg`. With the prompt enhancer on, the short prompt is expanded before generation.

```json
{
  "width": 1024,
  "height": 1024,
  "prompt": "a beautiful landscape",
  "use_pe": true,
  "num_outputs": 1,
  "output_format": "jpg",
  "guidance_scale": 4,
  "output_quality": 80,
  "num_inference_steps": 50
}
```

### Example Output
![Example output: a landscape generated by ERNIE-Image from a short prompt](https://blog.api.market/wp-content/uploads/2026/10/ernie-image-output-z5yy00d3-api-market.jpeg)

## Input Parameters
| Field | Type | Required | Default | Allowed values | Description |
| --- | --- | --- | --- | --- | --- |
| `prompt` | string | Yes |  |  | Text prompt for image generation. |
| `width` | integer | No | `1024` | 64 to 2048 | Width of the generated image. Best results come from the model-card recommended sizes. |
| `height` | integer | No | `1024` | 64 to 2048 | Height of the generated image. Best results come from the model-card recommended sizes. |
| `num_inference_steps` | integer | No | `50` | 1 to 100 | Number of inference steps. More steps take longer. |
| `guidance_scale` | number | No | `4` | 0 to 20 | Classifier-free guidance scale. Higher values follow the prompt more closely. |
| `use_pe` | boolean | No | `true` |  | Enable the prompt enhancer recommended by the model card. |
| `seed` | integer | No | none |  | Random seed. Set for reproducible generation. |
| `num_outputs` | integer | No | `1` | 1 to 4 | Number of output images to generate. |
| `output_format` | string | No | `jpg` | `png`, `jpg`, `webp` | Format of the output image. |
| `output_quality` | integer | No | `80` | 0 to 100 | Quality when saving the output image, from 0 to 100. |

## Pricing
- **Pay As You Go (PAYG) pricing**: you only pay for what you use.
- **Price**: $0.115 per API unit.
- **1 API unit = 1 request with up to 60 seconds of processing.** A request that runs longer is billed one more unit for each started 60-second block (for example, more than 60 and up to 120 seconds of processing is 2 units, $0.23).
- More images (`num_outputs`), larger sizes and more steps take longer and can add units.
- **Example cost**: the example request (one 1024x1024 image at 50 steps with the prompt enhancer on) took 34.6 seconds of processing, which fits in one 60-second block: 1 API unit, $0.115.
- **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/text-to-image-generator-prunaai-ernie-image`

### 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/text-to-image-generator-prunaai-ernie-image/predictions" \
  -H "Content-Type: application/json" \
  -H "x-api-market-key: YOUR_API_MARKET_KEY" \
  -d '{
    "version": "d5bfa4984edc317383025be5fd59a6a2d2b1992cf98bdddd788e5d5fa12a3ba4",
    "input": {
      "width": 1024,
      "height": 1024,
      "prompt": "a beautiful landscape",
      "use_pe": true,
      "num_outputs": 1,
      "output_format": "jpg",
      "guidance_scale": 4,
      "output_quality": 80,
      "num_inference_steps": 50
    }
  }'
```

Response (201 Created):
```json
{
  "id": "z5yy00d3ehrna0d1f1qa67ep5w",
  "version": "d5bfa4984edc317383025be5fd59a6a2d2b1992cf98bdddd788e5d5fa12a3ba4",
  "status": "starting",
  "created_at": "2026-10-26T13:37:59.354Z"
}
```

#### Check Prediction Status
```bash
curl -X GET "https://prod.api.market/api/v1/magicapi/text-to-image-generator-prunaai-ernie-image/predictions/{id}" \
  -H "x-api-market-key: YOUR_API_MARKET_KEY"
```

Response when the prediction has finished (200 OK):
```json
{
  "id": "z5yy00d3ehrna0d1f1qa67ep5w",
  "status": "succeeded",
  "output": [
    "https://blog.api.market/wp-content/uploads/2026/10/ernie-image-output-z5yy00d3-api-market.jpeg"
  ],
  "error": null,
  "created_at": "2026-10-26T13:37:59.354Z",
  "started_at": "2026-10-26T13:39:53.796Z",
  "completed_at": "2026-10-26T13:40:28.355Z"
}
```

`output` is an array of image URLs, one per generated image (`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 a missing `prompt`, a `width` above 2048 or `num_outputs` above 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
Requests are rate limited to keep usage fair. If you receive a 429 response, wait and retry with exponential backoff.

## 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/text-to-image-generator-prunaai-ernie-image";

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: "d5bfa4984edc317383025be5fd59a6a2d2b1992cf98bdddd788e5d5fa12a3ba4", 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": 1024,
  "height": 1024,
  "prompt": "a beautiful landscape",
  "use_pe": true,
  "num_outputs": 1,
  "output_format": "jpg",
  "guidance_scale": 4,
  "output_quality": 80,
  "num_inference_steps": 50
}).then((output) => output.forEach((url) => console.log(url)));
```

#### Python
```python
import time
import requests

API_KEY = "YOUR_API_MARKET_KEY"
BASE_URL = "https://prod.api.market/api/v1/magicapi/text-to-image-generator-prunaai-ernie-image"


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": "d5bfa4984edc317383025be5fd59a6a2d2b1992cf98bdddd788e5d5fa12a3ba4", "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({
    "width": 1024,
    "height": 1024,
    "prompt": "a beautiful landscape",
    "use_pe": True,
    "num_outputs": 1,
    "output_format": "jpg",
    "guidance_scale": 4,
    "output_quality": 80,
    "num_inference_steps": 50,
})
for url in output:
    print(url)
```

## FAQ
- **What does `use_pe` do?**
  - It runs the prompt enhancer recommended by the model card on your prompt before the image is generated. It is on by default; set it to `false` to use your prompt exactly as written.
- **What image sizes can I request?**
  - `width` and `height` each from 64 to 2048 pixels, default 1024 x 1024. The model card's recommended sizes give the best results.
- **How many images does one request return?**
  - Between 1 and 4, set by `num_outputs` (default 1). `output` is always a list of URLs.
- **How can I get the same image again?**
  - Send the same input with the same `seed`.
- **How much does a request cost?**
  - $0.115 for each started 60 seconds of processing. The example (one 1024x1024 image at 50 steps) took 34.6 seconds and cost 1 unit ($0.115); more images, larger sizes or more steps take longer and can add units.
- **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 or need assistance, you can reach out to us through the embedded chat on the bottom right corner of the page or send an email to hello@magicapi.com.


Generate images from text with Baidu ERNIE-Image: 1 to 4 images, 64 to 2048 px sizes, prompt enhancer and step control. $0.115 per request.