Experiments with Krea 2 :)
pre-release Turbo model produce the exact same outputs as the officially released but with a little something hidden inside to be found
Refiner Neutering: cancel the actions of the txtfusion.refiner_blocks from the model. From my limited testing it has a similar effet to using a txtfusion.projector bypass lora or the Conditioning Multiply node but without the color saturation or overcooked textures. Load the patch as a lora, always use at strength 1.
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support