# Krea 2 | Medium | Turbo | Text to Image

Krea 2 Medium Turbo generates high-fidelity images from text in seconds, with aspect ratio, creativity, and style-reference controls for fast visual ideation.

## API Information

- **Model Slug:** krea-v2-medium-turbo-text-to-image
- **Branded URL:** https://www.eachlabs.ai/krea/krea-v2/krea-v2-medium-turbo-text-to-image
- **Provider:** Krea
- **Category:** Text to Image
- **Output Type:** array
- **Status:** active
- **Base Cost:** $0.015–$0.0175 per image, depending on used image style references
- **Estimated Processing Time:** 25 seconds
- **Interactive Demo:** https://www.eachlabs.ai/ai-models/krea-v2-medium-turbo-text-to-image

## Pricing

- **Charge Type:** dynamic
- **Estimate:** $0.015–$0.0175 per image, depending on used image style references
- **Pricing Details:** used image style references: $0.0175
- **Pricing Details:** default: $0.015

## Input Schema

| Parameter | Type | Required | Default | Constraints | Description |
|-----------|------|----------|---------|-------------|-------------|
| prompt | string | Yes | - | - | Text description of the image to generate. |
| aspect_ratio | string | No | 1:1 | 1:1, 4:3, 3:2, 16:9, 2.35:1, 4:5, 2:3, 9:16 | Aspect ratio of the generated image. Default: 1:1. |
| creativity | string | No | medium | raw, low, medium, high | Controls how loosely the model interprets the prompt. Default: medium. |
| seed | integer | No | - | - | Random seed for reproducible generation. Leave empty for random output. |
| image_style_references | array | No | [] | - | Optional reference images that guide generated image style. At most 10 entries. |
| styles | array | No | [] | - | Optional Krea preset styles to apply. At most 10 entries. |
| moodboards | array | No | [] | - | Optional Krea moodboard to apply. At most one entry. |

## 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": "krea-v2-medium-turbo-text-to-image",
  "input": {
    "prompt": "dreamlike retro-futuristic coastline in the middle of a desert, champagne Porsche 911 parked beneath towering curved palm trees with oversized plush coral wheels partially submerged in reflective turquoise water, scattered seashell-colored rocks, pastel surfboards leaning against the car, warm pink sand dunes in the distance, intense cyan sky, glossy cinematic lighting, surreal luxury campaign aesthetic, hyperreal 3D render, exaggerated proportions"
  }
}'
```

## 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

**Krea 2 | Medium | Turbo | Text to Image Overview**

Krea 2 | Medium | Turbo | Text to Image is a fast, creative text-to-image generation model from Krea’s *krea v2* family, designed for real-time visual experimentation and high-iteration workflows. It converts natural language prompts into detailed images, helping creators, designers, and marketers explore visual concepts in seconds rather than minutes. Built around Krea’s focus on live, fluid image generation and granular control, this model balances speed with quality for everyday production tasks. On each::labs, Krea 2 | Medium | Turbo | Text to Image is ideal when you need rapid visual ideation, continuous prompt tweaking, and a responsive text-to-image API that fits into modern design and creative pipelines.

## 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.