Name: OpenDalle v1.1 API: Text to Image Generator
Brand: magicapi
SKU: api-magicapi-top-tier-ai-image-generator-lucataco-open-dalle-v1-1
Availability: InStock
Author: API Market

Shashank Agarwal

# 🎨 Text-to-Image Generator API (lucataco OpenDalle v1.1)

## Overview
OpenDalle v1.1 is a text-to-image model built on SDXL. Its developer describes it as a fusion of models with strong prompt adherence and semantic understanding, a step above base SDXL in prompt comprehension.

Send a `prompt` to generate images at the `width` and `height` you choose (1024 x 1024 by default). Add an `image` to transform it (image-to-image), or an `image` plus a `mask` to repaint only the white areas of the mask (inpainting). Each request returns a list of 1 to 4 image URLs, set by `num_outputs`.

## Features
- **Text to image**: `prompt` plus an optional `negative_prompt` (default "worst quality, low quality").
- **Image to image**: send `image`; `prompt_strength` (0 to 1, default 0.8) sets how much of it is replaced.
- **Inpainting**: send `image` and `mask`; black mask areas are kept and white areas are repainted.
- **Several images per request**: `num_outputs` from 1 to 4.
- **Sampler controls**: seven `scheduler` options, `num_inference_steps` (1 to 100, default 60) and `guidance_scale` (1 to 50, default 7.5).
- **Seed and watermark**: `seed` for repeatable results; `apply_watermark` (default `true`) marks images as generated.

## Use Cases
1. **Concept art and illustration**: characters, creatures and scenes from detailed prompts.
2. **Marketing images**: product backdrops and campaign visuals in custom sizes.
3. **Variations of an image**: restyle a sketch or photo with image-to-image.
4. **Fixing part of an image**: repaint a masked area with inpainting.

## Visual Examples
### Example Input
Prompt: "black fluffy gorgeous dangerous cat animal creature, large orange eyes, big fluffy ears, piercing gaze, full moon, dark ambiance, best quality, extremely detailed"

Settings: `width` 1024, `height` 1024, `num_outputs` 1, `scheduler` `KarrasDPM`, `num_inference_steps` 60, `guidance_scale` 7.5, `negative_prompt` "worst quality, low quality", `prompt_strength` 0.8, `apply_watermark` true.

### Example Output
![OpenDalle v1.1 output for the black fluffy cat prompt above](https://blog.api.market/wp-content/uploads/2026/10/open-dalle-v1-1-output-rrkf1wk4-api-market.jpg)

## Input Parameters
| Field | Type | Required | Default | Allowed values | Description |
| --- | --- | --- | --- | --- | --- |
| `prompt` | string | No | a sample prompt (a black fluffy cat under a full moon) |  | Input prompt |
| `negative_prompt` | string | No | `worst quality, low quality` |  | Things to keep out of the image |
| `image` | string (URL) | No | none |  | Input image URL (jpeg, png, gif or webp) for image-to-image or inpainting |
| `mask` | string (URL) | No | none |  | Mask image URL for inpainting. Black areas are kept, white areas are repainted. |
| `width` | integer | No | `1024` |  | Width of the output image in pixels |
| `height` | integer | No | `1024` |  | Height of the output image in pixels |
| `num_outputs` | integer | No | `1` | 1 to 4 | Number of images to generate |
| `scheduler` | string | No | `KarrasDPM` | `DDIM`, `DPMSolverMultistep`, `HeunDiscrete`, `KarrasDPM`, `K_EULER_ANCESTRAL`, `K_EULER`, `PNDM` | Sampling scheduler |
| `num_inference_steps` | integer | No | `60` | 1 to 100 | Number of denoising steps: 60 to 70 for the most detail, 35 for speed |
| `guidance_scale` | number | No | `7.5` | 1 to 50 | Scale for classifier-free guidance |
| `prompt_strength` | number | No | `0.8` | 0 to 1 | How much of the input image is replaced in image-to-image or inpainting. 1.0 replaces it completely. |
| `seed` | integer | No | none |  | Random seed. Leave blank to randomize. |
| `apply_watermark` | boolean | No | `true` |  | Apply a watermark that marks the image as generated. Set to false only if you have your own provisions for safe deployment. |
| `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**: $0.027 per API unit.
- **1 API unit = 1 request with up to 24 seconds of processing.** A request that takes longer is billed one more unit for each started 24-second block of processing time.
- **Example cost**: the example request above took 7.80 seconds of processing, which is 1 started 24-second block, so it cost 1 unit = $0.027.
- More outputs, more inference steps and larger sizes take longer and can use more units.
- **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/top-tier-ai-image-generator-lucataco-open-dalle-v1-1`

### 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/top-tier-ai-image-generator-lucataco-open-dalle-v1-1/predictions" \
  -H "Content-Type: application/json" \
  -H "x-api-market-key: YOUR_API_MARKET_KEY" \
  -d '{
    "version": "1c7d4c8dec39c7306df7794b28419078cb9d18b9213ab1c21fdc46a1deca0144",
    "input": {
      "width": 1024,
      "height": 1024,
      "prompt": "black fluffy gorgeous dangerous cat animal creature, large orange eyes, big fluffy ears, piercing gaze, full moon, dark ambiance, best quality, extremely detailed",
      "scheduler": "KarrasDPM",
      "num_outputs": 1,
      "guidance_scale": 7.5,
      "apply_watermark": true,
      "negative_prompt": "worst quality, low quality",
      "prompt_strength": 0.8,
      "num_inference_steps": 60
    }
  }'
```

Response (201 Created):
```json
{
  "id": "rrkf1wk4tnrmw0d1d12rv0tgz4",
  "version": "1c7d4c8dec39c7306df7794b28419078cb9d18b9213ab1c21fdc46a1deca0144",
  "status": "starting",
  "created_at": "2026-10-23T10:19:01.150Z"
}
```

#### Check Prediction Status
```bash
curl -X GET "https://prod.api.market/api/v1/magicapi/top-tier-ai-image-generator-lucataco-open-dalle-v1-1/predictions/{id}" \
  -H "x-api-market-key: YOUR_API_MARKET_KEY"
```

Response when the prediction has finished (200 OK):
```json
{
  "id": "rrkf1wk4tnrmw0d1d12rv0tgz4",
  "status": "succeeded",
  "output": [
    "https://blog.api.market/wp-content/uploads/2026/10/open-dalle-v1-1-output-rrkf1wk4-api-market.jpg"
  ],
  "error": null,
  "created_at": "2026-10-23T10:19:01.150Z",
  "started_at": "2026-10-23T10:19:53.877Z",
  "completed_at": "2026-10-23T10:20:01.675Z"
}
```

`output` is an array of image URLs, one per 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 `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/top-tier-ai-image-generator-lucataco-open-dalle-v1-1";

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: "1c7d4c8dec39c7306df7794b28419078cb9d18b9213ab1c21fdc46a1deca0144", 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": "black fluffy gorgeous dangerous cat animal creature, large orange eyes, big fluffy ears, piercing gaze, full moon, dark ambiance, best quality, extremely detailed",
    "scheduler": "KarrasDPM",
    "num_outputs": 1,
    "guidance_scale": 7.5,
    "apply_watermark": true,
    "negative_prompt": "worst quality, low quality",
    "prompt_strength": 0.8,
    "num_inference_steps": 60
  }).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/top-tier-ai-image-generator-lucataco-open-dalle-v1-1"


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": "1c7d4c8dec39c7306df7794b28419078cb9d18b9213ab1c21fdc46a1deca0144", "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": 1024,
    "height": 1024,
    "prompt": "black fluffy gorgeous dangerous cat animal creature, large orange eyes, big fluffy ears, piercing gaze, full moon, dark ambiance, best quality, extremely detailed",
    "scheduler": "KarrasDPM",
    "num_outputs": 1,
    "guidance_scale": 7.5,
    "apply_watermark": True,
    "negative_prompt": "worst quality, low quality",
    "prompt_strength": 0.8,
    "num_inference_steps": 60
}))
```

## FAQ
- **How many images does one request return?**
  - Between 1 and 4, set by `num_outputs` (default 1). They come back as a list of URLs.
- **How do I edit only part of an image?**
  - Send the image as `image` and a mask as `mask`. White areas of the mask are repainted from your prompt; black areas are kept.
- **What does `prompt_strength` do?**
  - In image-to-image and inpainting it sets how much of the input is replaced: 1.0 replaces everything, lower values keep more of the original.
- **How do I get faster results?**
  - Lower `num_inference_steps`. The model's own guidance is 60 to 70 steps for the most detail and 35 for speed.
- **Can I reproduce an image?**
  - Yes. Send the same `seed` with the same prompt and settings.

## 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 images per request from a text prompt with OpenDalle v1.1, or use it for image-to-image and inpainting. $0.027 per call, pay as you go.