index
:
textual-inversion-diff
master
textual-inversion-diff
summary
refs
log
tree
commit
diff
stats
log msg
author
committer
range
path:
root
/
data
Commit message (
Collapse
)
Author
Age
Files
Lines
*
Fix
Volpeon
2023-01-06
1
-2
/
+4
|
*
Update
Volpeon
2023-01-05
2
-21
/
+22
|
*
Update
Volpeon
2023-01-04
1
-1
/
+1
|
*
Various updates
Volpeon
2023-01-04
1
-18
/
+27
|
*
Fixed reproducibility, more consistant validation
Volpeon
2023-01-04
1
-3
/
+7
|
*
Fixed accuracy calc, other improvements
Volpeon
2023-01-01
1
-1
/
+1
|
*
Misc improvements
Volpeon
2022-12-30
1
-20
/
+20
|
*
Training script improvements
Volpeon
2022-12-30
1
-11
/
+4
|
*
Set default dimensions to 768; add config inheritance
Volpeon
2022-12-26
1
-2
/
+2
|
*
Update
Volpeon
2022-12-24
1
-8
/
+8
|
*
Fix
Volpeon
2022-12-24
1
-2
/
+2
|
*
Better dataset prompt handling
Volpeon
2022-12-23
1
-9
/
+16
|
*
num_class_images is now class images per train image
Volpeon
2022-12-23
1
-2
/
+2
|
*
Improved class prompt handling
Volpeon
2022-12-23
1
-17
/
+12
|
*
Dependency cleanup/upgrades
Volpeon
2022-12-20
1
-3
/
+2
|
*
Improved dataset prompt handling, fixed
Volpeon
2022-12-19
1
-18
/
+23
|
*
Avoid increased VRAM usage on validation
Volpeon
2022-12-15
1
-3
/
+10
|
*
More generic datset filter
Volpeon
2022-12-14
1
-5
/
+5
|
*
Optimized Textual Inversion training by filtering dataset by existence of ↵
Volpeon
2022-12-13
1
-7
/
+31
|
|
|
|
added tokens
*
Training improvements such as tag dropout
Volpeon
2022-12-11
1
-3
/
+10
|
*
Various updated; shuffle prompt content during training
Volpeon
2022-12-10
1
-9
/
+20
|
*
Update
Volpeon
2022-11-14
1
-1
/
+1
|
*
Update
Volpeon
2022-11-01
1
-10
/
+1
|
*
Added CLI arg to set dataloader worker num; improved text encoder handling ↵
Volpeon
2022-10-27
1
-3
/
+7
|
|
|
|
with Dreambooth
*
Advanced datasets
Volpeon
2022-10-24
1
-25
/
+39
|
*
Update
Volpeon
2022-10-24
1
-17
/
+16
|
*
Revert lat; fix skip attribute in dataset
Volpeon
2022-10-22
1
-1
/
+1
|
*
Improved prompt handling
Volpeon
2022-10-18
1
-46
/
+37
|
*
Implemented extended prompt limit
Volpeon
2022-10-17
1
-4
/
+10
|
*
Added support for Aesthetic Gradients
Volpeon
2022-10-13
1
-1
/
+1
|
*
Various updates
Volpeon
2022-10-12
1
-2
/
+1
|
*
Update
Volpeon
2022-10-08
1
-77
/
+85
|
*
Training: Create multiple class images per training image
Volpeon
2022-10-07
1
-14
/
+40
|
*
Update
Volpeon
2022-10-06
2
-150
/
+0
|
*
Add Textual Inversion with class dataset (a la Dreambooth)
Volpeon
2022-10-04
2
-25
/
+4
|
*
Bugfix
Volpeon
2022-10-04
1
-2
/
+2
|
*
Dreambooth: Generate specialized class images from input prompts
Volpeon
2022-10-03
3
-62
/
+57
|
*
Small perf improvements
Volpeon
2022-10-03
2
-4
/
+5
|
*
Added negative prompt support for training scripts
Volpeon
2022-10-03
2
-13
/
+19
|
*
Fixed euler_a generator argument
Volpeon
2022-10-03
2
-5
/
+9
|
*
Assign unused images in validation dataset to train dataset
Volpeon
2022-10-03
2
-5
/
+15
|
*
Use euler_a for samples in learning scripts; backported improvement from ↵
Volpeon
2022-10-03
2
-53
/
+46
|
|
|
|
Dreambooth to Textual Inversion
*
Batches of size 1 cause error: Expected query.is_contiguous() to be true, ↵
Volpeon
2022-09-28
1
-9
/
+9
|
|
|
|
but got false
*
Improved sample output and progress bars
Volpeon
2022-09-28
1
-5
/
+5
|
*
Various improvements, added inference script
Volpeon
2022-09-27
1
-0
/
+1
|
*
Supply dataset CSV file instead of dir with hardcoded CSV filename
Volpeon
2022-09-27
1
-10
/
+14
|
*
Added Dreambooth training script
Volpeon
2022-09-27
2
-0
/
+193
|
*
Undo textual inversion dataset improvements
Volpeon
2022-09-27
1
-10
/
+21
|
*
More cleanup
Volpeon
2022-09-27
1
-0
/
+134