# Flux Realism

Flux Realism focuses on generating hyper-realistic images for professional-grade visuals.

## API Information

- **Model Slug:** flux-dev-realism
- **Branded URL:** https://www.eachlabs.ai/black-forest-labs/flux-dev/flux-dev-realism
- **Provider:** Black Forest Labs
- **Category:** Text to Image
- **Output Type:** image
- **Status:** active
- **Base Cost:** $0.05 per execution
- **Estimated Processing Time:** 15 seconds
- **Interactive Demo:** https://www.eachlabs.ai/ai-models/flux-dev-realism

## Pricing

- **Charge Type:** dynamic
- **Estimate:** $0.05 per execution
- **Pricing Details:** default: $0.05

## Input Schema

| Parameter | Type | Required | Default | Constraints | Description |
|-----------|------|----------|---------|-------------|-------------|
| prompt | string | Yes | - | - | Text description of the image to generate. The model uses a realism LoRA for photorealistic results. Be specific about subject, style, lighting, and composition. |
| aspect_ratio | string | No | 1:1 | 1:1, 16:9, 21:9, 2:3, 3:2, 4:5, 5:4, 9:16, 9:21 | Image aspect ratio. 1:1: square 1024x1024 (default). 16:9: widescreen landscape. 9:16: portrait/mobile. 2:3/3:2: classic photo. 4:5/5:4: social media. 21:9/9:21: ultra-wide/tall. |
| num_outputs | integer | No | 1 | 1–4 | Number of images to generate per request (1-4). Default: 1. |
| num_inference_steps | integer | No | 30 | 1–100 | Number of denoising steps (1-100). Higher values produce more detailed images but take longer. Default: 30. |
| guidance | number | No | 3.5 | 0–30 | Controls prompt adherence (0-30). Higher values follow the prompt more closely. Default: 3.5 for realistic results. |
| lora_strength | number | No | 0.8 | 0–4 | Intensity of the realism LoRA effect (0-4). Higher values produce more photorealistic results. Default: 0.8. |
| output_format | string | No | webp | webp, jpg, png | Image output format. webp: modern compression (default). jpg: widely compatible. png: lossless, larger files. |
| output_quality | integer | No | 80 | 1–99 | Image compression quality (1-99). Higher values produce better quality but larger files. Default: 80. |
| seed | integer | No | - | 1–0 | Random seed for reproducible results. Same seed with identical parameters generates the same image. Leave empty for random. |

## 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-dev-realism",
  "input": {
    "prompt": "A photo of a woman, headshot, realistic"
  }
}'
```

## 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-dev-realism — Text to Image AI Model**

flux-dev-realism from Black Forest Labs delivers hyper-realistic text-to-image generation, producing professional-grade visuals that eliminate the typical "AI look" for photorealistic outputs ideal for designers and marketers seeking **Black Forest Labs text-to-image** solutions. Developed as part of the flux-dev family, this model excels in natural details and exceptional realism, supporting high-resolution images up to 1024x1024 and beyond on capable hardware. Users searching for a **text-to-image AI model** with superior aesthetics turn to flux-dev-realism for its ability to render lifelike scenes without oily highlights or unnatural artifacts, making it a top choice for realistic image creation.

## 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.