# Flux 2 | Lora Edit

A FLUX.2 [dev] image-to-image model with LoRA support, enabling specialized style transfer and precise domain-specific edits.

## API Information

- **Model Slug:** flux-2-lora-edit
- **Branded URL:** https://www.eachlabs.ai/black-forest-labs/flux-2/flux-2-lora-edit
- **Provider:** Black Forest Labs
- **Category:** Image to Image
- **Output Type:** array
- **Status:** active
- **Version:** 0.0.1
- **Base Cost:** Pricing is based on image size. Each megapixel of the generated image costs $0.021, and each megapixel of every input image is also charged at $0.021. Cost grows with the number of input and output images. Small images are billed as a single megapixel.
- **Estimated Processing Time:** 20 seconds
- **Last Updated:** 2026-04-28
- **Interactive Demo:** https://www.eachlabs.ai/ai-models/flux-2-lora-edit

## Pricing

- **Charge Type:** dynamic
- **Pricing Details:** Pricing is based on image size. Each megapixel of the generated image costs $0.021, and each megapixel of every input image is also charged at $0.021. Cost grows with the number of input and output images. Small images are billed as a single megapixel.

### Pricing Rules

| Condition | Pricing |
| --- | --- |
| output.width < "708" AND output.height < "708" | Pricing is based on image size. Each megapixel of the generated image costs $0.021, and each megapixel of every input image is also charged at $0.021. Cost grows with the number of input and output images. Small images are billed as a single megapixel. |
| Rule 2 | Pricing is based on image size. Each megapixel of the generated image costs $0.021, and each megapixel of every input image is also charged at $0.021. Cost grows with the number of input and output images. Small images are billed as a single megapixel. |

## Input Schema

| Parameter | Type | Required | Default | Constraints | Description |
|-----------|------|----------|---------|-------------|-------------|
| prompt | string | Yes | - | - | The prompt to generate an image from. |
| image_urls | array | Yes | - | 1–3 | The URsL of the images for editing. |
| loras | array | No | - | 0–3 | List of LoRA weights to apply (maximum 3) |
| guidance_scale | number | No | 2.5 | 0–20 | Guidance Scale is a measure of how close you want the model to stick to your prompt when looking for a related image to show you. |
| num_inference_steps | integer | No | 28 | 4–50 | The number of inference steps to perform. |
| image_size | string | No | square_hd | square_hd,square,portrait_4_3,portrait_16_9,landscape_4_3,landscape_16_9 | The size of the image to generate. |
| num_images | integer | No | 1 | 1–4 | The number of images to generate. |
| acceleration | string | No | regular | none,regular,high | The acceleration level to use for the image generation. |
| enable_prompt_expansion | boolean | No | false | - | If set to true, the prompt will be expanded for better results. |
| enable_safety_checker | boolean | No | true | - | If set to true, the safety checker will be enabled. |
| output_format | string | No | png | jpeg,png,webp | The format of the generated image. |
| seed | integer | No | - | - | The seed to use for the generation. If not provided, a random seed will be used |

## Example Request

```bash
curl -X POST https://api.eachlabs.ai/v1/prediction/ \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "flux-2-lora-edit",
  "input": {
    "image_urls": [
      "https://storage.googleapis.com/magicpoint/inputs/flux-2-lora-edit-input.png"
    ],
    "prompt": "Make this  ice cream realistic"
  }
}'
```

## Output Schema

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

```json
{
  "status": "success",
  "predictionID": "string",
  "output": "array",
  "metrics": {
    "predict_time": "number (seconds)"
  }
}
```

## Polling

```bash
curl https://api.eachlabs.ai/v1/prediction/{PREDICTION_ID} \
  -H "Authorization: Bearer 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 `Authorization` bearer token |
| `404` | Unknown model or prediction id |
| `429` | Rate limit — 100 creates / min, 10 concurrent per key |
| `5xx` | Retry with backoff |

## Overview

**flux-2-lora-edit — Image-to-Image AI Model**

flux-2-lora-edit, a specialized variant of Black Forest Labs' FLUX.2 [klein] 9B Edit with LoRA support, empowers developers and creators to perform precise image-to-image edits using natural language instructions and custom style adapters.flux-2-lora-edit stands out in the competitive landscape of **image-to-image AI models** by combining a 9 billion parameter rectified flow transformer with undistilled training, enabling superior customization for domain-specific edits like style transfer and multi-reference compositions.

Developed as part of the flux-2 family, this model addresses key pain points in AI photo editing for e-commerce and design workflows, delivering photorealistic results with up to 4 reference images while supporting LoRA adapters for personalized visual identities. Whether you're building an **AI image editor API** or automating product mockups, flux-2-lora-edit offers sub-second inference on consumer hardware, making high-fidelity edits accessible without heavy computational demands.

## Usage Notes

- API Base URL: `https://api.eachlabs.ai/v1`
- Authentication: send `Authorization: Bearer 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.