eycab

Kandinsky 3.1 has updated a few new features(including Kandinsky Flash) a few weeks ago which is yet supported in diffusers. Please check out https://github.com/ai-forever/Kandinsky-3

It seems your get_T2I_Flash_pipeline requires more than 40G memory in a A100 GPU when trying to inference.However,when I tried to load the model in 2*40G A100 GPU,it seems your codes...

Any plans on make it available for paralleled processing like paradigms or even better a turbo version?

1

Thank you for your contribution on this project. Yet, I can't help wondering if you have any plans on make it available for paralleled processing like paradigms or even better...

hubert 中文配适模型有没直接开源可用的？

1

目前，facebook 的hubert-large-ls960-ft 好像不支持中文的，腾讯的chinese-hubert-large 缺少tokenizer词表，问下还有没其他开源方案在这块可以直接支持中文可用的？