city96
Requesting a new model (Kandinsky 2.2)
Hi! Really appreciate the effort gone into producing these nodes, I was wondering if you had any plans to support models based on Kandinsky 2.2? Would really like to try it out and build new workflows since the quality and image blending is superior to most models :)
Interesting. I've briefly looked at 3 before but it needed some other flavor of T5 that looked annoying to implement. This one just seems to use CLIP though. I'll see what I can do.
Awesome! The great thing about Kandinsky is the Apache-2 license and the ability to train controllers and loras - it just hasn't gained enough traction as SDXL but seems to be at par on the quality and flexibility! Looking forward to updates whenever possible :)