ai-forever / Kandinsky-3

Home Page:https://ai-forever.github.io/Kandinsky-3/

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Do you provide a code tutorial on finetuning models

trouble-maker007 opened this issue · comments

Are there also training tutorials for LoRa and ControlNet?

You can refer to https://github.com/huggingface/diffusers. In the new version they added Kandinsky 3.0, So, you can utilize tutorials from diffusers

Still it got nothing about the code to finetune this one. i think they will launch 3.1 with better diffusion quality. 3.0 in fact under performed against kandinsky 2.2. so all we need to do is to wait...