blub

README.md

@@ -131,7 +131,7 @@ see experiment 3.0. restarted from 0 with `--proportion_empty_prompts=0.5` => re
 
 resumed from 45000 steps with left-right flipped images until 90000 steps => results are still not good, 50% is probably also too much for 90k steps. guessmode still doesn't work and tends to produces humans. aborting.
 
-** Experiment 5.0 - 2023-09-28 - control-edgedrawing-cv480edpf-fastdup-fp16-checkpoint-45000 **
+**Experiment 5.0 - 2023-09-28 - control-edgedrawing-cv480edpf-fastdup-fp16-checkpoint-45000**
 
 see experiment 3. cleaned original images following the [fastdup introduction](https://nbviewer.org/github/visual-layer/fastdup/blob/main/examples/cleaning-image-dataset.ipynb) resulting in:
 ```
@@ -146,13 +146,13 @@ see experiment 3. cleaned original images following the [fastdup introduction](h
 
 restarted from 0 with left-right flipped images and `--mixed-precision="no"` to create a master release and converted to fp16 afterwards.
 
-** Experiment 6.0 - control-edgedrawing-cv480edpf-rect-fp16-checkpoint-XXXXX **
+**Experiment 6.0 - control-edgedrawing-cv480edpf-rect-fp16-checkpoint-XXXXX**
 
 see experiment 5.0.
 * included images with aspect ratio > 2
 * resized images with shortside to 512 which gives us rectangular images instead of 512x512 squares
 * center-cropped images to 512x(n)*64 (to make them SD compatible) and max longside 1024
-* sorted duplicates by `similarity` value from `laion2b-en-aesthetics65` to get the best `text` of all duplicates
+* sorted duplicates by `similarity` value from `laion2b-en-aesthetics65` to get the best `text` from all the duplicates
 
 ```
 183410 images in total

control-edgedrawing-cv480edpf-fastdup-fp16-checkpoint-45000.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3bbf59b6d52bd7c9bda5e3c9f206d16e6244fad35827152d09377a0f63d0363a
+size 4323252