Krea 2 Turbo Training Adapter This is a training adapter designed to be used for fine tuning krea/Krea 2 Turbo. It was made for use with AI Toolkit but could potentially be used in other trainers as well. If you are implementing it into training code and have questions. I am always happy to help. Just reach out. Why is it needed? When you train directly on a step distilled model, the distillation breaks down very quickly. This results in losing the step distillation in an unpredictable way. A de distill training adapter slows this process down significantly allowing you to do short training runs while preserving the step distillation (speed). You could also train directly on the raw model, but training directly on the turbo model could yield better results. What is the catch? This is really just a hack to significantly slow down the distillation when fine tuning a distilled model. The distillation will still be broken down over time. What that means is, this adapter will work great for shorter runs such as styles, concepts, and characters. However, doing a long training run will likely lead to the distillation breaking down to a point where artifacts will be produced when the adapt…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy