lhjlhj11
lhjlhj11
请问下具体需要怎么操作呢 ，发现通过自己的摸索，出来的效果都很差
That is to say, it can be solved if I use some specific OCR methods.
> > Could be related, but I noticed the latest release of optimum-quanto (v0.2.5) corrupts transformer weights during qfloat8 quantization. Downgrading to 0.2.4 solved this issue. Not sure what the...
> Can you try with `diffusers` installation from `main`? > > ```shell > pip uninstall diffusers -y > pip install git+https://github.com/huggingface/diffusers > ``` The problem is still exit after this...
> Do you have a minimal reproducible snippet? The provided one isn't minimal and self-contained. I keep asking for that because we have an integration test for Kohya LoRAs here:...
> @tyyff if you could help me with a minimally reproducible snippet that would be great, ideally with a supported quantization backend like `bitsandbytes`. Can you solve the problems with...
> @tyyff if you could help me with a minimally reproducible snippet that would be great, ideally with a supported quantization backend like `bitsandbytes`. Or can diffusers under 0.32.0 support...