# FLUX HF LoRA

FLUX.1-Dev  LoRA is text to image AI model designed for precise image generation and fine-tuning.

## API Information

- **Model Slug:** flux-hf-lora
- **Branded URL:** https://www.eachlabs.ai/black-forest-labs/flux-lora/flux-hf-lora
- **Provider:** Black Forest Labs
- **Category:** Text to Image
- **Output Type:** image
- **Status:** active
- **Version:** 0.0.1
- **Base Cost:** Per-second pricing based on provider predict_time. Rate: $0.00154/sec from GPU tier.
- **Estimated Processing Time:** 90 seconds
- **Last Updated:** 2026-07-13
- **Interactive Demo:** https://www.eachlabs.ai/ai-models/flux-hf-lora

## Pricing

- **Charge Type:** dynamic
- **Pricing Details:** Per-second pricing based on provider predict_time. Rate: $0.00154/sec from GPU tier.

### Pricing Rules

| Condition | Pricing |
| --- | --- |
| Rule 1 | Per-second pricing based on provider predict_time. Rate: $0.00154/sec from GPU tier. |

## 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 (or denoising strength) when using image to image. 1.0 corresponds to full destruction of information in image. |
| num_outputs | integer | No | 1 | 1–4 | Number of images to output. |
| num_inference_steps | integer | No | 28 | 0–50 | Number of inference steps |
| guidance_scale | number | No | 3.5 | 0–10 | Guidance scale for the diffusion process |
| 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 |
| hf_lora | string | No | - | - | HF, Replicate, CivitAI, or URL to a LoRA. Ex: alvdansen/frosting_lane_flux |
| lora_scale | number | No | 0.8 | 0–1 | Scale for the LoRA weights |
| disable_safety_checker | boolean | No | true | - | Disable safety checker for generated images. This feature is only available through the API. See [https://replicate.com/docs/how-does-replicate-work#safety](https://replicate.com/docs/how-does-replicate-work#safety) |

## 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-hf-lora",
  "input": {
    "prompt": "a beautiful castle frstingln illustration"
  }
}'
```

## 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

**flux-hf-lora — Text-to-Image AI Model**

flux-hf-lora, a specialized LoRA adaptation of Black Forest Labs' FLUX.1-Dev within the flux-lora family, enables precise text-to-image generation and fine-tuning for custom styles, characters, or concepts on consumer hardware. This **text-to-image AI model** excels in inheriting the base model's strengths like accurate text rendering and coherent compositions while allowing efficient personalization through low-rank adaptation. Developers seeking a "Black Forest Labs text-to-image LoRA" or "flux-lora fine-tuning" find flux-hf-lora ideal for injecting domain-specific details without retraining massive models, supporting high-resolution outputs up to 4 megapixels.

Built on the rectified flow transformer architecture of FLUX.1-Dev—a 12 billion parameter model tuned for quality—flux-hf-lora uses LoRA rank configurations like 128 with scaling factor 256 for targeted adaptations. It addresses common pain points in image generation, such as inconsistent styles across batches, by enabling quick fine-tuning on datasets for consistent branding or artistic renders.

## 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.