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

update readme to reflect everydream trainer no longer works optimally with cropped images

This commit is contained in:
Victor Hall 2022-11-19 18:48:55 -05:00
parent a0952762c9
commit 33cd24f394
2 changed files with 5 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
doc/AUTO_CAPTION.md
View File

@ -4,7 +4,11 @@ Automatic captioning uses Salesforce's BLIP to automatically create a clean sent
This requires an Nvidia GPU, but is not terribly intensive work. It should run fine on something like a 1050 Ti 4GB.
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.
[EveryDream trainer](https://github.com/victorchall/EveryDream-trainer) no longer requires cropped images. You only need to crop to exclude stuff you don't want trained, or to improve the portion of face close ups in your data. The EveryDream trainer now accepts multiple aspect ratios and can train on them natively.
But if you do wish to crop for other trainers, you can use [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. There are various tools out there for this.
## Execute

2
doc/LAION_SCRAPE.md
View File

@ -37,8 +37,6 @@ Script should be reasonably fast depending on your internet speed. I'm able to
## Other resources
Easy resize/crop tool: [Birme](https://www.birme.net/?target_width=512&target_height=512&auto_focal=false&image_format=webp&quality_jpeg=95&quality_webp=99)
Nvidia has compiled a close up photo set: [ffhq-dataset](https://github.com/NVlabs/ffhq-dataset)
## Batch run