Skip to content

Krea · Image

Krea 2 Turbo

KreaImageOpen weights. The weights are publicly available in a Hugging Face repo.
From Venice's listing:
Krea 2 Turbo is the speed-optimized, open-weight version of Krea's Krea 2 image model, generating high-fidelity images at 1K or 2K in seconds. It suits rapid ideation and iteration.
Market median price
$0.008 /image
Listings
8
Providers
5

Evidence and sources

🤗 krea/Krea-2-TurboReleased 18 Jun 2026
Sources: LMArena data, Venice.ai data, Hugging FacePrimary data from LMArena from Venice.ai: primary mode, description from Hugging Face: release date

Advantages and trade-offs

Compared with 10 representative image models

Advantages

Open weights available

The weights are public. 0 of the 5 peers that say either way have open weights.

We only make a claim when there's enough data on models of the same type. Updated 22 Nov, 06:07 UTC.Prices come from the model's maker where they sell it, otherwise their official partner, otherwise the market median. This comparison uses 2 maker's prices; 8 market median prices.

Input & output

as stated by the model's providers
Text
Images
Images

Listings

 NanoGPTkrea-2/turboSource: NanoGPTNot published by the provider$0.008
 NanoGPTkrea-v2/turbo-lora · loraSource: NanoGPTNot published by the provider$0.018
 fal.aifal-ai/krea-2/turboSources: Fal.ai data, LiteLLM dataNot published by the provider$0.008
 fal.aifal-ai/krea-2/turbo/lora · loraSources: Fal.ai data, LiteLLM dataNot published by the provider$0.01

4 listings without a price are hidden.

Benchmarks

Named effort levels run from lowest to highest. Select a result to see its source details.

Image generation

Human preference

Data credits: LMArena, CC BY 4.0 (licence)

Also known as: fal-ai/krea-2/turbo, fal-ai/krea-2/turbo/lora, krea 2 turbo, krea-2-turbo-lora, krea-2/turbo, krea-v2-turbo, krea-v2/turbo, krea-v2/turbo-lora

Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works