alexfredo
alexfredo
Yeah that would be awesome ! textual inversion can run under 6gb too
There's no error message I just don't have the style I have train
For example my command style in the prompt is "skchan style" it's work on hugging face but on automatic1111 it's completely ignored
it's 2.1 I used this for generate the checkpoint https://huggingface.co/spaces/multimodalart/dreambooth-training
I guess 2.1 dreambooth are not supported for the moment ?
I have noticed that the dreambooth 2.1 is highly superior to the dreambooth 1.5 so I really hope this will be fixed soon. I get medium result with 1.5 and...
On the stable diffusion github there's write that "To enable fp16 (which can cause numerical instabilities with the vanilla attention module on the v2.1 model) , run your script with...
I made another checkpoint with the 2.1 and this time I have a error message when I add --no-half : Error completing request Arguments: ('tanaka2 style', '', 'None', 'None', 20,...
Do someone else have the same problem that me ? the dreambooth style of 2.1 is still ignored, please someone helps
Yes I tried but I have a error when I pip install the requirement too : 