G-force78

> [issue 2889](https://github.com/AUTOMATIC1111/stable-diffusion-webui/issues/2889) mentions the same problem. i have it as well. it seems to be related to shareable gradio links timing out at some point when using the `--share`...

> I'm using this one locally. https://github.com/nadermx/backgroundremover An Integration would be awesome. Looks good will take a look thanks!

> he inpainting model _can_ be used for pure `txt2img` and `img2img` but in my experience the standard 1.5 model produces better results. I'm not convinced that is not purely...

> > I'm not convinced that is not purely subjective > > It's mostly subjective. How do we implicitly prove that one model outperforms the other? My opinion is supported...

You can use the command line in this one, need to change the paths in the YAML to your own. https://colab.research.google.com/drive/1e_LpbLCcgHEuvKXiw9G2XNTho3xB6ceK#scrollTo=DJxzTyuKbIX1

> We don't have a specific plan to release this part of codes by now, but we do encourage the community to implement and PR. In your original demo on...

Not sure if related but now get this error RuntimeError: Detected that PyTorch and torchvision were compiled with different CUDA versions. PyTorch has CUDA Version=11.7 and torchvision has CUDA Version=11.6....

I would like to know how to convert a ckpt for use with JAX and TPU in the flaxpipeline.

Have you tried changing this to the exact path in your environment? ./pretrained_model/wav2vec2-base-960h/config.json

> @Klace I saw today on Automatic the preparations to support webUI. Thank you very much and I look forward to hearing more, because this is another level where we...