today, we release the open weights of Krea 2.
welcome Krea 2 Raw and Krea 2 Turbo, an undistilled model from mid-training meant to be fine-tuned, and a fast distilled version with a wide aesthetic diversity.
read the details below 👇
we are releasing two versions of our foundation image model: Krea 2 Raw and Krea 2 Turbo.
combined, they bring unprecedented opportunities for fine-tuning, post-training, and working with diverse aesthetics.
the core idea is: train on Raw, generate with Turbo.
Krea 2 Raw is an undistilled model from mid-training stage that we created while training Krea 2 Medium.
The lack of distillation, fine-tuning, or post-training make it an ideal model to build on.
Krea 2 Turbo is a distilled and post-trained version of Krea 2 Medium.
This model can produce imagery in a wide range of aesthetics fast at 2k native resolution, and it can run in consumer hardware.
open weights — A model whose trained parameters are published for anyone to download and run — unlike API-only models you can access but never possess.
fine-tuning — Taking a trained model and training it a bit more on your own examples so it gets better at one specific job.
distillation — Training a small, cheap model to imitate a big one's outputs, keeping much of the capability at a fraction of the cost.
Why it matters
You can fine-tuningTaking a trained model and training it a bit more on your own examples so it gets better at one specific job.Full definition → on Raw and serve with Turbo instead of renting a closed image API, with 2K generation on consumer hardware and a license permitting commercial use by individuals and small companies.
Read the full thread on X ↗
