Qing

https://lama-cleaner-docs.vercel.app/install/windows_1click_installer

Which model are you using? And what do you mean by `blackens the marked area or transforms it`? A snapshot of the web page would be helpful

Prompt needs to contain the object you want to paint, and the context around it to make Stable diffusion inpainting work better. You can try just use `background` as prompt...

SD model runs really slow on CPU devices, I suggest using `--device mps`. 1. Install the latest lama-cleaner via pip: `pip install lama-cleaner==0.30.0` 2. Make sure to follow the requirements...

 pytorch's package name is `torch` :smile: `pip install torch==1.13.0` This is no output directory in lama-cleaner...If the model run successful, you can click download button on the bottom 

Combine with [cropper feature](https://lama-cleaner-docs.vercel.app/features/croper_resize), sd1.5 run on M2 chip 1.5it/s (512x512) image size

This looks like a docker error log, I suggest you try `sleep infinity` as entry point to start the container and see if it starts successfully

> could not select device driver "" with capabilities: [[gpu]]. I found an issue on the Nvidia-docker GitHub repository, which might be helpful [could not select device driver "" with...

> I have a self defined model that use a integrated query_key_value layer: > > ```python > self.query_key_value = skip_init( > torch.nn.Linear, > hidden_size, > 3 * self.inner_hidden_size, > bias=bias,...

@djaym7 hi, Did you solve this problem?