Mykeehu

Same problem here under Windows

Have any solution for this problem? I use batch size to 4 now, but if there is a more secure solution, I would appreciate it. I am currently using [this...

Thank you for solution! I thought this was only true for CPU mode, and since I wanted to process it with GPU, I didn't type it.

See the topics below: For style: https://github.com/AUTOMATIC1111/stable-diffusion-webui/discussions/2284 and https://github.com/AUTOMATIC1111/stable-diffusion-webui/discussions/2670 For image: https://github.com/AUTOMATIC1111/stable-diffusion-webui/discussions/1528

There is a solution in last line: > Torch is not able to use GPU; add --skip-torch-cuda-test to COMMANDLINE_ARGS variable to disable this check Edit webui-user.bat and add this command...

However, AMD cards don't have CUDA (which is why I switched from AMD to NVIDIA). [Here's a description for Linux](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Install-and-Run-on-AMD-GPUs) and [here's for Windows](https://rentry.org/ayymd-stable-diffustion-v1_4-guide) for AMD cards, I don't know...

Add a new block after loaded model.ckpt and you can fill more than one model (waifu 1.2 is unfortunately on a slow server, but 1.3 is better for anime): !wget...

Change this under Settings tab, while colab is running, it remembers the settings. I don't use addon commands on the colab.

In the latest version (1ed227b3b57f06f4152be3bfc9f83b0a839a2604) the problem with embedding was so bad that it was generating noise on the third model, nothing to do with the images. After closing SD...

When I stop the training and then create the file again using the "Overwrite Old Embedding" option, the embedding is not reloaded, the training does not start from the beginning,...