K

Krea-2-Turbo

All-around model

No ratings yet(0 ratings)Sign in to vote
View on Hugging FaceBack to Image Models

Model Information

Model Type

KREA2

Model Class

KREA2

Recommended Sampler

Default

Recommended Steps

8

Recommended CFG

0.5

CLIP Skip

1

Requests (24h)

2K

Requests (7d)

17K

Capabilities

Image to image, IP-Adapter

Added At

8/4/2026

Recommended Negative Prompt

lowres, bad anatomy, bad hands, text, error, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry

Use Krea-2-Turbo with the Arli AI API

Generate images with Krea-2-Turbo through the OpenAI-style image endpoint. Send sd_model_checkpoint as the model name and the API renders the result without logging your prompts.

cURL

curl -X POST https://api.arliai.com/v1/txt2img \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $ARLIAI_API_KEY" \
  -d '{
    "sd_model_checkpoint": "Krea-2-Turbo",
    "prompt": "a red fox in fresh snow, cinematic light",
    "negative_prompt": "lowres, bad anatomy, watermark",
    "steps": 8,
    "sampler_name": "Default",
    "cfg_scale": 0.5,
    "width": 1024,
    "height": 1024
  }'

Python

import requests

response = requests.post(
    "https://api.arliai.com/v1/txt2img",
    headers={"Authorization": "Bearer YOUR_ARLIAI_API_KEY"},
    json={
        "sd_model_checkpoint": "Krea-2-Turbo",
        "prompt": "a red fox in fresh snow, cinematic light",
        "steps": 8,
        "sampler_name": "Default",
        "cfg_scale": 0.5,
        "width": 1024,
        "height": 1024,
    },
)
print(response.json())

See the image generation docs for every parameter, or read the quick start guide to make your first request.