Name: Pruna AI P-Image-Edit-LoRA LoRA Image Editing API
Brand: magicapi
SKU: api-magicapi-image-edit-lora-api-prunaai-p-image-edit-lora
Availability: InStock
Author: API Market

Shashank Agarwal

# ✏️ LoRA Image Editing API (Pruna AI P-Image-Edit-LoRA)

## Overview
P-Image-Edit-LoRA is an image editing model from Pruna AI that applies a trained LoRA (a small set of add-on weights) while it edits your images. The LoRA teaches the model a specific edit or style, such as a dotted illustration look, and your text `prompt` describes the edit.

Send one or more reference `images` (the first one is the image to edit), a `prompt` and the URL of the LoRA in `lora_weights`. Each request returns the URL of one edited image.

## Features
- **LoRA-driven edits**: load LoRA weights from a HuggingFace URL in the format `huggingface.co/<owner>/<model-name>[/<lora-weights-file.safetensors>]`.
- **LoRA strength**: `lora_scale` (-1 to 3, default `1`) sets how strongly the LoRA is applied.
- **Several reference images**: pass a list in `images`; the prompt can refer to them as "image 1", "image 2" and so on.
- **Aspect ratios**: `match_input_image` (default, matches the first image), `1:1`, `16:9`, `9:16`, `4:3`, `3:4`, `3:2`, `2:3`.
- **Turbo mode**: `turbo` (default `true`) runs faster with extra optimizations; the model's developer recommends turning it off for complicated edits.
- **Seed**: set `seed` to reproduce a result.

## Use Cases
1. **Apply a house style**: convert product photos or illustrations into one consistent look with a style LoRA.
2. **Repeatable edits**: run the same trained edit over many images by reusing the same `lora_weights` and `prompt`.
3. **Combine references**: describe an edit that uses elements from two or more images in `images`.
4. **Test your own LoRAs**: try LoRAs you trained for this model on real images before using them in production.

## Visual Examples
### Example Input
Image to edit: ![Example input: a bird photo used as the image to edit](https://blog.api.market/wp-content/uploads/2026/10/supir-input-api-market.png)

Prompt: "dotted illustration"

LoRA: `https://huggingface.co/davidberenstein1957/p-image-edit-dotted-illustration-lora/resolve/main/weights.safetensors` with `lora_scale` `1`, `aspect_ratio` `match_input_image`, `turbo` `true`.

### Example Output
![P-Image-Edit-LoRA output: the bird photo redrawn as a dotted illustration](https://blog.api.market/wp-content/uploads/2026/11/p-image-edit-lora-output-jnn4pvw1-api-market.jpeg)

## Input Parameters
| Field | Type | Required | Default | Allowed values | Description |
| --- | --- | --- | --- | --- | --- |
| `prompt` | string | Yes |  |  | Text prompt for the edit. Describe the edit task clearly. You can refer to the images as 'image 1', 'image 2' and so on |
| `images` | array of strings (URL) | No | `[]` |  | Images to use as a reference. For an editing task, put the main image first |
| `turbo` | boolean | No | `true` |  | Run faster with additional optimizations. For complicated tasks, turning this off is recommended |
| `aspect_ratio` | string | No | `match_input_image` | `match_input_image`, `1:1`, `16:9`, `9:16`, `4:3`, `3:4`, `3:2`, `2:3` | Aspect ratio of the generated image. `match_input_image` matches the aspect ratio of the first image |
| `seed` | integer | No | none |  | Random seed. Set it for reproducible generation |
| `disable_safety_checker` | boolean | No | `false` |  | Disable the safety checker for generated images |
| `lora_weights` | string | Yes |  |  | LoRA weights to load. Supports HuggingFace URLs in the format huggingface.co/&lt;owner&gt;/&lt;model-name&gt;[/&lt;lora-weights-file.safetensors&gt;] |
| `lora_scale` | number | No | `1` | -1 to 3 | How strongly the LoRA is applied |

## Pricing
- **Pay As You Go (PAYG) pricing**: you only pay for what you use.
- **Price**: $0.012 per API unit.
- **1 API unit = 1 output image.** Each request returns one image (no input changes the count), so each successful request costs $0.012.
- The example request above returned 1 image and cost $0.012.
- **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/image-edit-lora-api-prunaai-p-image-edit-lora`

### 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/image-edit-lora-api-prunaai-p-image-edit-lora/predictions" \
  -H "Content-Type: application/json" \
  -H "x-api-market-key: YOUR_API_MARKET_KEY" \
  -d '{
    "version": "prunaai/p-image-edit-lora",
    "input": {
      "turbo": true,
      "images": ["https://blog.api.market/wp-content/uploads/2026/10/supir-input-api-market.png"],
      "prompt": "dotted illustration",
      "lora_scale": 1,
      "aspect_ratio": "match_input_image",
      "lora_weights": "https://huggingface.co/davidberenstein1957/p-image-edit-dotted-illustration-lora/resolve/main/weights.safetensors"
    }
  }'
```

Response (201 Created):
```json
{
  "id": "jnn4pvw17nrmw0d1mvnrbq2r0m",
  "version": "prunaai/p-image-edit-lora",
  "status": "starting",
  "created_at": "2026-11-04T14:16:54.333Z"
}
```

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

Response when the prediction has finished (200 OK):
```json
{
  "id": "jnn4pvw17nrmw0d1mvnrbq2r0m",
  "status": "succeeded",
  "output": "https://blog.api.market/wp-content/uploads/2026/11/p-image-edit-lora-output-jnn4pvw1-api-market.jpeg",
  "error": null,
  "created_at": "2026-11-04T14:16:54.333Z",
  "started_at": "2026-11-04T14:16:54.351Z",
  "completed_at": "2026-11-04T14:16:58.476Z"
}
```

`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` or `lora_weights`, or a `lora_scale` outside -1 to 3.
- **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`, for example when the LoRA URL cannot be loaded; 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/image-edit-lora-api-prunaai-p-image-edit-lora";

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: "prunaai/p-image-edit-lora", 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({
  turbo: true,
  images: ["https://blog.api.market/wp-content/uploads/2026/10/supir-input-api-market.png"],
  prompt: "dotted illustration",
  lora_scale: 1,
  aspect_ratio: "match_input_image",
  lora_weights: "https://huggingface.co/davidberenstein1957/p-image-edit-dotted-illustration-lora/resolve/main/weights.safetensors"
}).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/image-edit-lora-api-prunaai-p-image-edit-lora"


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": "prunaai/p-image-edit-lora", "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({
    "turbo": True,
    "images": ["https://blog.api.market/wp-content/uploads/2026/10/supir-input-api-market.png"],
    "prompt": "dotted illustration",
    "lora_scale": 1,
    "aspect_ratio": "match_input_image",
    "lora_weights": "https://huggingface.co/davidberenstein1957/p-image-edit-dotted-illustration-lora/resolve/main/weights.safetensors"
}))
```

## FAQ
- **Which LoRAs can I use?**
  - LoRAs trained for P-Image-Edit, loaded from a public HuggingFace URL in `lora_weights`. Point to the `.safetensors` file or to the model repository.
- **Which image gets edited when I send several?**
  - The first image in `images` is the main image. Refer to the others in the prompt as "image 2", "image 3" and so on.
- **How strong should `lora_scale` be?**
  - The default is `1`. Lower it to soften the LoRA's effect, raise it (up to 3) to strengthen it; negative values down to -1 are also accepted.
- **How many images does one request return?**
  - One. Each image is billed as one API unit ($0.012).
- **What if my prediction fails?**
  - Failed predictions are not billed. Read the `error` field, check that the LoRA URL is reachable, 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 Pruna AI's P-Image-Edit-LoRA: load a trained LoRA from HuggingFace, send your images and a prompt, get one edited image. $0.012 per image, pay as you go.