# Pruna | P-Image Edit LoRA | Image Editing

Pruna P-Image Edit LoRA combines premium image editing with custom LoRA support.

## API Information

- **Model Slug:** p-image-edit-lora-image-edit
- **Branded URL:** https://www.eachlabs.ai/pruna/p-image/p-image-edit-lora-image-edit
- **Provider:** Pruna AI
- **Category:** Image to Image
- **Output Type:** image
- **Status:** active
- **Version:** 0.0.1
- **Base Cost:** $0.01 per edited image
- **Estimated Processing Time:** 8 seconds
- **Last Updated:** 2026-04-02
- **Interactive Demo:** https://www.eachlabs.ai/ai-models/p-image-edit-lora-image-edit

## Pricing

- **Charge Type:** dynamic
- **Estimated Price (default example):** $0.0100
- **Pricing Details:** $0.01 per edited image

### Pricing Rules

| Condition | Pricing |
| --- | --- |
| Rule 1 | $0.01 per edited image |

## Input Schema

| Parameter | Type | Required | Default | Constraints | Description |
|-----------|------|----------|---------|-------------|-------------|
| prompt | string | Yes | - | - | Text prompt describing the edit. Refer to images as image 1, image 2, etc. |
| images | array | Yes | - | 1–5 | Array of 1-5 image URLs for editing. |
| lora_weights | string | No | - | - | HuggingFace URL to LoRA weights. Must be trained with p-image-edit-trainer. |
| lora_scale | number | No | 1 | - | LoRA strength (-1 to 3). Default 1 for edit LoRAs. |
| hf_api_token | string | No | - | - | HuggingFace API token for accessing private LoRA repositories. |
| turbo | boolean | No | true | - | Faster optimizations. Set false for complex tasks. |
| aspect_ratio | string | No | match_input_image | match_input_image,1:1,16:9,9:16,4:3,3:4,3:2,2:3 | Output aspect ratio. match_input_image: match input image ratio (default). |
| seed | integer | No | - | - | Random seed for reproducible generation. |
| disable_safety_checker | boolean | No | false | - | Disable safety checker for generated images. |

## Example Request

```bash
curl -X POST https://api.eachlabs.ai/v1/prediction/ \
  -H "X-API-Key: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "p-image-edit-lora-image-edit",
  "input": {
    "prompt": "A young Asian woman with long dark hair wearing an ornate vintage dress with burgundy and pink stripe patterns, intricate lace ruffle straps, sweetheart neckline, and floral damask print, standing in a soft studio setting with neutral background, elegant and composed pose, soft natural lighting, fashion editorial photography style, photorealistic, 4K KEEP THE FACE SAME ",
    "images": [
      "https://storage.googleapis.com/magicpoint/inputs/p-image-edit-lora-image-edit-person-input.jpg",
      "https://storage.googleapis.com/magicpoint/inputs/p-image-edit-lora-image-edit-clothes-input.jpg"
    ]
  }
}'
```

## Output Schema

Response returned by `GET /v1/prediction/{id}` when the job completes:

```json
{
  "status": "success",
  "predictionID": "string",
  "output": "string (URL of generated image)",
  "metrics": {
    "predict_time": "number (seconds)"
  }
}
```

## Polling

```bash
curl https://api.eachlabs.ai/v1/prediction/{PREDICTION_ID} \
  -H "X-API-Key: YOUR_API_KEY"
```

| Status | Meaning |
|--------|---------|
| `processing` | Still running — poll again |
| `success` | Done — read `output` |
| `error` | Failed — read `message` / `details` |

## Webhook (alternative to polling)

Pass `"webhook_url": "https://your.host/path"` in the create request. Eachlabs POSTs this payload when the job ends:

```json
{
  "exec_id": "prediction-uuid",
  "status": "succeeded",
  "output": "https://...",
  "error": ""
}
```

`status` is `"succeeded"` or `"failed"`. `exec_id` equals the `predictionID` from create. Return 2xx within 30 seconds.

## Errors

Error body: `{ "status": "error", "message": "...", "details": "..." }`

| Code | Meaning |
|------|---------|
| `400` | Invalid input |
| `401` | Missing / invalid `X-API-Key` |
| `404` | Unknown model or prediction id |
| `429` | Rate limit — 100 creates / min, 10 concurrent per key |
| `5xx` | Retry with backoff |

## Overview

The **Pruna | P-Image Edit LoRA | Image Editing** model from Pruna enables precise image-to-image transformations using custom LoRA adaptations for targeted edits. Part of the P-Image family, it solves common challenges in AI image editing by combining premium editing capabilities with lightweight LoRA fine-tuning, allowing users to adapt styles or modifications without full model retraining. This **Pruna image-to-image** tool stands out for its efficiency in handling custom styles on consumer hardware, making high-quality edits accessible via APIs on platforms like each::labs.

Developed by Pruna, it leverages LoRA technology—Low-Rank Adaptation—for fast, resource-efficient customization. Ideal for creators needing quick iterations on images, it supports seamless integration into workflows on each::labs (eachlabs.ai). Whether enhancing details or applying artistic changes, this model delivers consistent results with minimal overhead.

## Usage Notes

- API Base URL: `https://api.eachlabs.ai/v1`
- Authentication: send `X-API-Key: YOUR_API_KEY`. Generate a key from the Eachlabs dashboard at https://www.eachlabs.ai/dashboard/api-keys.
- File-typed parameters (`*_url`, `image_url`, `video_url`, `audio_url`, etc.) accept publicly-reachable HTTPS URLs only. Upload your asset first (GCS / S3 / your CDN) and pass the resulting URL. Data-URIs and localhost URLs are rejected.
- For structured parameters (arrays / objects) send real JSON values, not stringified payloads.
- Monetary values are reported in USD; per-token / per-megapixel rates may be billed in micro-cents internally.
- Prefer `webhook_url` over polling for long-running predictions — see the Webhook Callback section.