# Krea 2 | Medium | Text to Image

Krea 2 Medium generates aesthetic, stylized images from text prompts, with strong results for illustration, anime, and painterly art on each::labs.

## API Information

- **Model Slug:** krea-v2-medium-text-to-image
- **Branded URL:** https://www.eachlabs.ai/krea/krea-v2/krea-v2-medium-text-to-image
- **Provider:** Krea
- **Category:** Text to Image
- **Output Type:** array
- **Status:** active
- **Version:** 0.0.1
- **Base Cost:** Krea 2 Medium text-to-image: $0.030 per generated image
- **Estimated Processing Time:** 25 seconds
- **Last Updated:** 2026-06-01
- **Interactive Demo:** https://www.eachlabs.ai/ai-models/krea-v2-medium-text-to-image

## Pricing

- **Charge Type:** dynamic
- **Estimated Price (default example):** $0.0300
- **Pricing Details:** Krea 2 Medium text-to-image: $0.030 per generated image

### Pricing Rules

| Condition | Pricing |
| --- | --- |
| output.used_image_style_references == "true" | Krea 2 Medium with image_style_references: $0.035 per generated image |
| Rule 2 | Krea 2 Medium text-to-image: $0.030 per generated image |

## Input Schema

No input parameters documented.

## 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-text-to-image",
  "input": {}
}'
```

## 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 | Text to Image Overview**

Krea 2 | Medium | Text to Image is a text-to-image generation model from Krea’s *krea v2* family, focused on producing aesthetic, stylized artwork from natural language prompts. It is optimized for illustration, anime-inspired visuals, and painterly art styles, making it a strong choice for creators who prioritize style and mood over strict photorealism. On each::labs, Krea 2 | Medium | Text to Image helps users turn short or detailed prompts into fully rendered images with consistent artistic direction. The model aims to balance quality and speed, providing reliable outputs suitable for concept art, social visuals, and creative experimentation without the heavy setup overhead of custom 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.