Name: Pruna AI HiDream-E1.1 Image Editing API
Brand: magicapi
SKU: api-magicapi-edit-image-with-prompt-prunaai-hidream-e1-1
Availability: InStock
Author: API Market

Shashank Agarwal

# 🖌️ Prompt-Based Image Editing API (Pruna AI HiDream-E1.1)

## Overview
HiDream-E1.1 is an instruction-based image editing model. This version is published by Pruna AI, which describes it as HiDream-E1.1 accelerated with its optimisation engine.

Send an `image` URL and a text `prompt` that describes the change (for example "Convert the image into a 3D animated style."). Each request returns the URL of one edited image in webp, jpg or png.

## Features
- **Edit with plain instructions**: describe the change you want in `prompt`.
- **Speed modes**: `speed_mode` chooses between `Lightly Juiced 🍊 (more consistent)`, `Juiced 🔥 (more speed)` (default) and `Extra Juiced 🚀 (even more speed)`.
- **Guidance controls**: `guidance_scale` (0 to 10, default 2.5) sets how strongly the prompt is followed; `image_guidance_scale` (0 to 10, default 1) sets how strongly the input image is kept.
- **Refinement**: `refine_strength` (0 to 1, default 0.3) sets the strength of the refinement step; `clip_cfg_norm` (default `true`) turns CLIP CFG normalization on or off.
- **Steps**: `num_inference_steps` from 1 to 1000 (default 28).
- **Output format**: `webp` (default), `jpg` or `png`, with `output_quality` from 1 to 100 (default 100) for jpg and webp.
- **Seed**: set `seed` to reproduce a result; `-1` (default) picks a random seed.

## Use Cases
1. **Style changes**: turn a photo into a 3D animated, illustrated or painted look.
2. **Product and marketing images**: change backgrounds, colors or details of an existing image with a sentence.
3. **Content variations**: make several edited versions of one image for testing or social posts.
4. **Creative tools**: add prompt-based photo editing to an app without building an editing pipeline.

## Visual Examples
### Example Input
`image`:

![Example input: a giraffe photo](https://blog.api.market/wp-content/uploads/2026/10/rmgb-input-api-market.jpg)

Prompt: "Convert the image into a 3D animated style."

Other fields: `seed` 42, `speed_mode` `Extra Juiced 🚀 (even more speed)`, `clip_cfg_norm` `true`, `output_format` `webp`, `guidance_scale` 3.5, `output_quality` 80, `refine_strength` 0.3, `num_inference_steps` 28, `image_guidance_scale` 2.

### Example Output
![HiDream-E1.1 output: the giraffe photo converted into a 3D animated style](https://blog.api.market/wp-content/uploads/2026/11/hidream-e1-1-output-0qjqhqyv-api-market.webp)

## Input Parameters
| Field | Type | Required | Default | Allowed values | Description |
| --- | --- | --- | --- | --- | --- |
| `prompt` | string | Yes |  |  | Prompt describing the edit |
| `speed_mode` | string | No | `Juiced 🔥 (more speed)` | `Lightly Juiced 🍊 (more consistent)`, `Juiced 🔥 (more speed)`, `Extra Juiced 🚀 (even more speed)` | Speed optimization level |
| `image` | string (URL) | No | none |  | Input image to edit |
| `seed` | integer | No | `-1` |  | Random seed (-1 for random) |
| `output_format` | string | No | `webp` | `png`, `jpg`, `webp` | Output format |
| `output_quality` | integer | No | `100` | 1 to 100 | Output quality (for jpg and webp) |
| `guidance_scale` | number | No | `2.5` | 0 to 10 | Guidance scale |
| `num_inference_steps` | integer | No | `28` | 1 to 1000 | Number of inference steps |
| `image_guidance_scale` | number | No | `1` | 0 to 10 | Image guidance scale |
| `refine_strength` | number | No | `0.3` | 0 to 1 | Strength of refinement |
| `clip_cfg_norm` | boolean | No | `true` |  | Whether to use CLIP CFG normalization |

The schema does not mark `image` as required, but it is the image the model edits, so send it with every request.

## Pricing
- **Pay As You Go (PAYG) pricing**: you only pay for what you use.
- **Price**: $0.048 per API unit.
- **1 API unit = 1 successful request with up to 28 seconds of processing time.** Longer jobs bill one more unit for each started 28-second block of processing, so a request that needs 28.1 to 56 seconds of processing costs 2 units ($0.096).
- Processing time depends on `num_inference_steps`, `speed_mode` and the image size. Time spent waiting in the queue is not billed.
- **Example cost**: the example request took 98.54 seconds of processing, which is 4 API units (four started 28-second blocks), so it cost $0.192.
- **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/edit-image-with-prompt-prunaai-hidream-e1-1`

### 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 2 seconds and an overall timeout of 600 seconds (10 minutes) work well. The example request finished about 5 minutes after it was created, including time in the queue.

### Endpoints

#### Create a Prediction
```bash
curl -X POST "https://prod.api.market/api/v1/magicapi/edit-image-with-prompt-prunaai-hidream-e1-1/predictions" \
  -H "Content-Type: application/json" \
  -H "x-api-market-key: YOUR_API_MARKET_KEY" \
  -d '{
    "version": "433436facdc1172b6efcb801eb6f345d7858a32200d24e5febaccfb4b44ad66f",
    "input": {
      "image": "https://blog.api.market/wp-content/uploads/2026/10/rmgb-input-api-market.jpg",
      "prompt": "Convert the image into a 3D animated style.",
      "seed": 42,
      "speed_mode": "Extra Juiced 🚀 (even more speed)",
      "clip_cfg_norm": true,
      "output_format": "webp",
      "guidance_scale": 3.5,
      "output_quality": 80,
      "refine_strength": 0.3,
      "num_inference_steps": 28,
      "image_guidance_scale": 2
    }
  }'
```

Response (201 Created):
```json
{
  "id": "0qjqhqyvmhrp40d1mvnatbcy90",
  "version": "433436facdc1172b6efcb801eb6f345d7858a32200d24e5febaccfb4b44ad66f",
  "status": "starting",
  "created_at": "2026-11-04T14:16:11.940Z"
}
```

#### Check Prediction Status
```bash
curl -X GET "https://prod.api.market/api/v1/magicapi/edit-image-with-prompt-prunaai-hidream-e1-1/predictions/{id}" \
  -H "x-api-market-key: YOUR_API_MARKET_KEY"
```

Response when the prediction has finished (200 OK):
```json
{
  "id": "0qjqhqyvmhrp40d1mvnatbcy90",
  "status": "succeeded",
  "output": "https://blog.api.market/wp-content/uploads/2026/11/hidream-e1-1-output-0qjqhqyv-api-market.webp",
  "error": null,
  "created_at": "2026-11-04T14:16:11.940Z",
  "started_at": "2026-11-04T14:19:27.506Z",
  "completed_at": "2026-11-04T14:21:06.046Z"
}
```

`output` is a single URL string pointing to the edited 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 `prompt`, a `speed_mode` that is not in the list or a `guidance_scale` above 10.
- **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/edit-image-with-prompt-prunaai-hidream-e1-1";

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: "433436facdc1172b6efcb801eb6f345d7858a32200d24e5febaccfb4b44ad66f", 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 = 2000;
  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/rmgb-input-api-market.jpg",
  "prompt": "Convert the image into a 3D animated style.",
  "seed": 42,
  "speed_mode": "Extra Juiced 🚀 (even more speed)",
  "clip_cfg_norm": true,
  "output_format": "webp",
  "guidance_scale": 3.5,
  "output_quality": 80,
  "refine_strength": 0.3,
  "num_inference_steps": 28,
  "image_guidance_scale": 2
}).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/edit-image-with-prompt-prunaai-hidream-e1-1"


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": "433436facdc1172b6efcb801eb6f345d7858a32200d24e5febaccfb4b44ad66f", "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 = 2
    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/rmgb-input-api-market.jpg",
    "prompt": "Convert the image into a 3D animated style.",
    "seed": 42,
    "speed_mode": "Extra Juiced 🚀 (even more speed)",
    "clip_cfg_norm": True,
    "output_format": "webp",
    "guidance_scale": 3.5,
    "output_quality": 80,
    "refine_strength": 0.3,
    "num_inference_steps": 28,
    "image_guidance_scale": 2
}))
```

## FAQ
- **How do I write a good edit prompt?**
  - Describe the change as an instruction, for example "Convert the image into a 3D animated style." The input `image` supplies everything you do not mention.
- **The result changed too much (or too little) of my image. What should I adjust?**
  - Raise `image_guidance_scale` to keep more of the input image, or raise `guidance_scale` to follow the prompt more strongly. Both range from 0 to 10.
- **Which `speed_mode` should I use?**
  - `Lightly Juiced 🍊 (more consistent)` favors consistency, `Juiced 🔥 (more speed)` is the default, and `Extra Juiced 🚀 (even more speed)` is the fastest. Send the value exactly as listed, including the emoji.
- **How much does one edit cost?**
  - $0.048 for each started 28-second block of processing time. The example edit took 98.54 seconds of processing and cost $0.192 (4 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.


Edit images with a text instruction using HiDream-E1.1 in Pruna AI's accelerated version, with speed modes, guidance controls and webp, jpg or png output. $0.048 per 28 seconds of processing, pay as you go.