No module named 't2i_adapters'

[kopyl]

I just want to launch Kohya-ss LoRA inference on a clean GPU server.

Any way i can do this?

[kopyl]

I was trying to reverse-engineer your code to just get the inference with LoRA, but it seems like there is no end in filling the empty spaces

[kopyl]

I was able to get 0 errors and add LoRA.

But the results are WAAY worse than using LoRA in WebUI.

How to achieve the same quality in Python?

[OmegaTwiddle]

I was able to pull that dependency using

pip install git+https://github.com/cloneofsimo/t2i-adapter-diffusers

HTH