Jeremy Richards
Results
3
comments of
Jeremy Richards
trafficstars
When training the second person did you change the name of the hardcoded token "sks"? https://github.com/XavierXiao/Dreambooth-Stable-Diffusion/blob/main/ldm/data/personalized.py#L10
I'm not sure what dataset you are training on or what hardware you're using but what I see here is a pretty decent gradual slope that probably has a way...
> I think you need to change batch size I'm currently using `--batch_size 1 `