index
:
textual-inversion-diff
master
textual-inversion-diff
summary
refs
log
tree
commit
diff
stats
log msg
author
committer
range
path:
root
/
training
/
util.py
Commit message (
Expand
)
Author
Age
Files
Lines
*
Restored LR finder
Volpeon
2023-01-20
1
-143
/
+3
*
Update
Volpeon
2023-01-17
1
-8
/
+3
*
Restored functional trainer
Volpeon
2023-01-15
1
-3
/
+5
*
Update
Volpeon
2023-01-14
1
-112
/
+0
*
WIP: Modularization ("free(): invalid pointer" my ass)
Volpeon
2023-01-14
1
-96
/
+118
*
TI: Prepare UNet with Accelerate as well
Volpeon
2023-01-14
1
-8
/
+8
*
Cleanup
Volpeon
2023-01-14
1
-15
/
+11
*
More modularization
Volpeon
2023-01-13
1
-6
/
+9
*
Removed PromptProcessor, modularized training loop
Volpeon
2023-01-13
1
-1
/
+12
*
Fixed aspect ratio bucketing; allow passing token IDs to pipeline
Volpeon
2023-01-08
1
-6
/
+8
*
Improved aspect ratio bucketing
Volpeon
2023-01-08
1
-1
/
+1
*
Made aspect ratio bucketing configurable
Volpeon
2023-01-07
1
-7
/
+2
*
Added progressive aspect ratio bucketing
Volpeon
2023-01-07
1
-2
/
+2
*
Update
Volpeon
2023-01-06
1
-6
/
+6
*
Use context manager for EMA, on_train/eval hooks
Volpeon
2023-01-06
1
-1
/
+1
*
Add contextmanager to EMAModel to apply weights temporarily
Volpeon
2023-01-06
1
-0
/
+12
*
Added EMA to TI
Volpeon
2023-01-05
1
-5
/
+95
*
Added multi-vector embeddings
Volpeon
2022-12-31
1
-4
/
+56
*
Integrated updates from diffusers
Volpeon
2022-12-28
1
-5
/
+0
*
Code simplifications, avoid autocast
Volpeon
2022-12-25
1
-57
/
+49
*
Fix
Volpeon
2022-12-24
1
-1
/
+1
*
Fix again
Volpeon
2022-12-24
1
-1
/
+1
*
Fix
Volpeon
2022-12-24
1
-1
/
+4
*
Improved class prompt handling
Volpeon
2022-12-23
1
-3
/
+1
*
Moved common training code into separate module
Volpeon
2022-12-21
1
-0
/
+131