Krea 2 Medium Turbo
Neural Network
Krea 2 Medium Turbo is a Krea model for text-to-image generation, focused on speed and rapid iterations.
Specifications
- Input
- text, images
- Output
- images
- Resolution
- 1K, 2K, 4K
- Aspect ratio
- 1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 16:9, 9:16, 21:9
How it works Krea 2 Medium Turbo?
Krea 2 Medium Turbo is a distilled, high-speed version of Krea 2 Medium by the Krea team. It differs from the original model in generation speed, making it ideal for frequent iterations and exploring visual ideas rather than a single final render. This mode is useful in graphic design when you need to review many options quickly. In BotHub, the model is accessible from Russia without a VPN or foreign card; payment is in rubles, pay-as-you-go, no subscription, and unused funds do not expire. Over 250 models are available in one window, allowing easy switching and comparison of results for a single prompt. The unified BotHub API simplifies integration into your editor or pipeline, while companies get access to contracts, invoices, electronic document management, and an admin panel with limits. It is useful for designers creating draft banners and covers, marketers generating illustration options for landing pages and presentations, and teams for quick mood board creation and visual experiments when an idea is easier to see than to describe.Frequently asked questions about Krea 2 Medium Turbo
You can use generated results for commercial purposes. You own all rights to the content you create. The only restriction: make sure your prompt does not include copyrighted third-party material. You are responsible for respecting the rights to any input data.
The model creates images from text descriptions and processes existing images when a reference is provided. It is suitable for illustrations, concept art, covers, advertising layouts, and quick visualization of ideas. In BotHub, it is available alongside other models with pay-as-you-go billing, no VPN or foreign subscription required.
Exact resolution values and a list of formats are not specified in the model data, so please refer to the generation settings in the BotHub interface. The model works in two modes: creating images from text descriptions and processing uploaded images using a reference.
Our data does not indicate a reasoning mode, which is expected: krea-2-medium-turbo is a generative image model, not a text assistant. It outputs an image immediately based on a description or reference, without intermediate steps, explanations, or text responses.
Function calling and structured JSON output are not indicated in our data: these are tools for text and agent models, whereas krea-2-medium-turbo creates images. If your system requires function calling or JSON output, connect a suitable text model via the same BotHub API.
Yes, the model accepts images—this is confirmed in our data, so reference-based work is available. We have no record of audio or video input, so we cannot confirm that such files are accepted. Text descriptions for generation are also supported.
The model data contains no information about prompt and output languages, so we cannot promise perfect understanding of Russian—please test it with your task. The BotHub platform itself is localized in Russian: the interface, support, and payment with Russian cards in rubles, without VPN or foreign subscriptions.