Krea 2

by Krea AI

Krea 2 (Turbo) is the 8-step distilled variant of Krea AI's Krea 2, a 13B-parameter dense Diffusion Transformer text-to-image model. It generates in roughly two seconds, pairing the Qwen Image VAE with a Qwen3-VL text encoder that uses multi-layer feature aggregation, and natively renders 1K-2K resolution (up to 2 MP). Distributed under the Krea 2 Community License — per Krea's announcement, commercial use is free for teams under 50 seats; see the license for binding terms.

ImageKrea 2 Community LicenseReleased Jun 202613B parameters

Hugging Face repo ↗Krea AI ↗

Drag or click to move along the pipeline

full qualitylightest

Lighter tiers fit smaller GPUs and lose some detail. Start with the heaviest one that loads.

The model

Krea 2

BF1633.0 GB

Three pieces, three separate downloads.

Diffusion modelGoes in diffusion_models/

Generates the image

24.5 GB↓↗

Text encoderGoes in text_encoders/

Turns your prompt into guidance

8.3 GB↓↗

VAEGoes in vae/

Decodes the result into pixels

0.2 GB↓↗

LoRAs (optional)Goes in loras/

0.4 GB↓↗

SamplerKSampler

Copy these values into your KSampler.

Steps8

CFG1

Samplereuler

Schedulersimple

Denoise1

Native res.1024x1024 (native 1K-2K, up to 2 MP)

Usage notes

GGUF is the lightest way to run this model.

Krea 2 Community License. Check the official repo for usage terms.

Click a file name to copy it.