Mirrors
/
EveryDream
mirror of https://github.com/victorchall/EveryDream.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

update readme

This commit is contained in:
Victor Hall 2022-10-30 22:04:03 -04:00
parent 2b0d75792f
commit fac465060d
1 changed files with 1 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
doc/AUTO_CAPTION.md
View File

@ -6,12 +6,6 @@ This requires an Nvidia GPU, but is not terribly intensive work. It should run
I suggest using [Birme](https://www.birme.net/?target_width=512&target_height=512&auto_focal=false&image_format=webp&quality_jpeg=95&quality_webp=99) to crop and resize first, but there are various tools out there for this. I strongly suggest making sure to crop well for training! It's best to crop to square first because you do not want to caption things that are later removed by cropping. I suggest using [Birme](https://www.birme.net/?target_width=512&target_height=512&auto_focal=false&image_format=webp&quality_jpeg=95&quality_webp=99) to crop and resize first, but there are various tools out there for this. I strongly suggest making sure to crop well for training! It's best to crop to square first because you do not want to caption things that are later removed by cropping.
Auto-caption is fast and not very resource intensive, but it still uses GPU. You only need an Nvidia GPU with 2GB VRAM to run.
Make sure cuda version of torch and torchvision are installed by activating your environment and running this command:
pip install torch==1.12.1+cu113 torchvision==0.13.1+cu113 --extra-index-url https://download.pytorch.org/whl/cu113
## Execute ## Execute
Place input files into the /input folder Place input files into the /input folder