martin chan

Results 9 comments of martin chan

I managed to fix this by changing the docker image tag to "1.10.0-cuda11.3-cudnn8-devel"

This could be resolved with the following commands: ``` mkdir -p /MY-DATA-DIR && cd /MY-DATA-DIR mkdir models outputs sudo chown 10000:$UID -R models outputs sudo chmod 775 -R models outputs...

1. That would require multiple user support. I'm not quite familiar with it, but I could have a look. 2. This PR can restore progress for both txt2img and img2img....

1. It seems like back-end support would be a more appropriate way on this ... 2. Okay 3. No problem

I've made some changes based on the feedback I received. For (1), I updated the Task API to be user-specific when authentication is enabled. This means that users won't be...

Have you tried using the pre-built image?

@Muxelmann You can just install the dependencies by running the container in an interactive shell. e.g: ``` docker run -it --name sdw --gpus all --network host \ -v $(pwd)/models:/app/stable-diffusion-webui/models \...

> This thing doesn't work for me. Half the time to swapped event isn't emited and dropping the element doesn't do anything. Sometimes it seems to work after a hot...

Sorry to hear about that, currently there have been changes in the way releases are related to the CUDA version. Previously, each release was tied to CUDA version 12.1.1. Could...