# Black Forest Labs | Flux Dev Lora

A version of flux-dev, a text to image model, that supports fast fine-tuned lora inference

## API Information

- **Model Slug:** black-forest-labs-flux-dev-lora
- **Branded URL:** https://www.eachlabs.ai/black-forest-labs/flux/black-forest-labs-flux-dev-lora
- **Provider:** Black Forest Labs
- **Category:** Text to Image
- **Output Type:** image
- **Status:** active
- **Version:** 0.0.1
- **Base Cost:** $0.032 per output (input.num_outputs, default 1)
- **Estimated Processing Time:** 40 seconds
- **Last Updated:** 2026-06-10
- **Interactive Demo:** https://www.eachlabs.ai/ai-models/black-forest-labs-flux-dev-lora

## Pricing

- **Charge Type:** dynamic
- **Estimated Price (default example):** $0.0320
- **Pricing Details:** $0.032 per output (input.num_outputs, default 1)

### Pricing Rules

| Condition | Pricing |
| --- | --- |
| Rule 1 | $0.032 per output (input.num_outputs, default 1) |

## Input Schema

| Parameter | Type | Required | Default | Constraints | Description |
|-----------|------|----------|---------|-------------|-------------|
| prompt | string | Yes | - | - | Prompt for generated image |
| aspect_ratio | string | No | 1:1 | 1:1,16:9,21:9,3:2,2:3,4:5,5:4,3:4,4:3,9:16,9:21 | An enumeration. |
| image | string | No | - | - | Input image for image to image mode. The aspect ratio of your output will match this image |
| prompt_strength | number | No | 0.8 | 0–1 | Prompt strength when using img2img. 1.0 corresponds to full destruction of information in image |
| num_outputs | integer | No | 1 | 1–4 | Number of outputs to generate |
| num_inference_steps | integer | No | 28 | 1–50 | Number of denoising steps. Recommended range is 28-50, and lower number of steps produce lower quality outputs, faster. |
| guidance | number | No | 3 | 0–10 | Guidance for generated image |
| seed | integer | No | - | - | Random seed. Set for reproducible generation |
| output_format | string | No | webp | webp,jpg,png | An enumeration. |
| output_quality | integer | No | 80 | 0–100 | Quality when saving the output images, from 0 to 100. 100 is best quality, 0 is lowest quality. Not relevant for .png outputs |
| disable_safety_checker | boolean | No | false | - | Disable safety checker for generated images. |
| go_fast | boolean | No | false | - | Run faster predictions with model optimized for speed (currently fp8 quantized); disable to run in original bf16. Note that outputs will not be deterministic when this is enabled, even if you set a seed. |
| lora_weights | string | No | - | - | Load LoRA weights. Supports Replicate models in the format <owner>/<username> or <owner>/<username>/<version>, HuggingFace URLs in the format huggingface.co/<owner>/<model-name>[/<lora-weights-file.safetensors>], CivitAI URLs in the format civitai.com/models/<id>[/<model-name>], or arbitrary .safetensors URLs from the Internet, including signed URLs. For example, 'fofr/flux-pixar-cars'. Civit AI and HuggingFace LoRAs may require an API token to access, which you can provide in the `civitai_api_token` and `hf_api_token` inputs respectively. |
| lora_scale | number | No | 1 | 0–3 | Determines how strongly the main LoRA should be applied. Sane results between 0 and 1 for base inference. For go_fast we apply a 1.5x multiplier to this value; we've generally seen good performance when scaling the base value by that amount. You may still need to experiment to find the best value for your particular lora. |
| extra_lora | string | No | - | - | Load LoRA weights. Supports Replicate models in the format <owner>/<username> or <owner>/<username>/<version>, HuggingFace URLs in the format huggingface.co/<owner>/<model-name>, CivitAI URLs in the format civitai.com/models/<id>[/<model-name>], or arbitrary .safetensors URLs from the Internet. For example, 'fofr/flux-pixar-cars' |
| extra_lora_scale | number | No | 1 | 0–3 | Determines how strongly the extra LoRA should be applied. Sane results between 0 and 1 for base inference. For go_fast we apply a 1.5x multiplier to this value; we've generally seen good performance when scaling the base value by that amount. You may still need to experiment to find the best value for your particular lora. |
| megapixels | string | No | 1 | 1,0.25 | An enumeration. |
| hf_api_token | string | No | - | - | HuggingFace API token. If you're using a hf lora that needs authentication, you'll need to provide an API token. |
| civitai_api_token | string | No | - | - | Civitai API token. If you're using a civitai lora that needs authentication, you'll need to provide an API token. |

## 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": "black-forest-labs-flux-dev-lora",
  "input": {
    "prompt": "style of 80s cyberpunk, a portrait photo"
  }
}'
```

## 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 "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

**black-forest-labs-flux-dev-lora — Text to Image AI Model**

Developed by Black Forest Labs as part of the FLUX family, black-forest-labs-flux-dev-lora is a text-to-image generation model optimized for fast, fine-tuned LoRA inference. This model combines the power of Black Forest Labs' rectified flow transformer architecture with Low-Rank Adaptation support, enabling creators and developers to generate high-quality images while maintaining custom style control through personalized LoRA adapters. Unlike standard text-to-image models that require full model retraining for style customization, black-forest-labs-flux-dev-lora supports efficient LoRA fine-tuning, making it ideal for teams building AI image generation APIs or applications that demand both speed and visual consistency.

The model addresses a core challenge in production image generation: balancing inference speed with output quality while enabling style personalization without prohibitive computational costs. Whether you're building an AI image editor, powering e-commerce product visualization, or developing creative tools, black-forest-labs-flux-dev-lora delivers photorealistic results with the flexibility of custom LoRA adapters applied at inference time.

## 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.