sudo apt install python3-venv
pthon -m pip install virtualenv
cd ~
mkdir dreambooth
cd dreambooth
virtualenv -p python3 venv
source venv/bin/activate
pip install autotrain-advanced torchvision
autotrainer setup
check if ou need to use a slightly earlier transformers/bits and bytes from what ou have ( it noted in m error)
put your imagss inn a /images folder, and run the autotrainer with the default hugginface settings.. hange the instance prompt string to your own prompt, and voila.
autotrain dreambooth --model stabilityai/stable-diffusion-xl-base-1.0 \
--project-name my_dreambooth_project --image-path images/ \
--prompt "photo of a <YOUR_PROMPT> <YOUR_CLASS>" \
--resolution 1024 --batch-size 1 \
--num-steps 500 --gradient-accumulation 2 \
--lr 0.00001 --fp16 --xformers \
--train-text-encoder --use-8bit-adam \
--gradient-checkpointing
i'm tryingto use in Kaggle, but this message appears
upgraded, 4 newly installed, 0 to remove and 69 not upgraded.
Need to get 9849 kB of archives.
After this operation, 2982 kB of additional disk space will be used.
Do you want to continue? [Y/n]
i press Y but didnt work
How can i install in silent mode?