silverhammer751
silverhammer751
I think he's saying that when he tries to have a batch count higher than 1 he's getting CUDA errors. I'm getting them too. I can generate one image, but...
I've found that I sometimes have to restart my PC to get textual inversions to train faster. After a while (especially if I'm doing several in a row) it starts...
I solved my problem by switching to 3.10.6.
I ran into the problem again, and the issue was that the name of the embedding wasn't found in the prompt (I use filenames). Renamed the files and it worked.
When I ran into the issue after switching to 3.10.6, I discovered that my embedding name and the name I used in the filewords weren't lining up (e.g. my filenames...
When you train the embedding, it'll have a "Prompt template file." In the file you use, you need it to include [name] or, if you use [filewords] include the name...
I'm getting this issue too across multiple commits. Is it a graphics card driver issue? I heard NVidia made some changes and I'm wondering if that's causing this.