JC_Array
|
f53f703aeb
|
resolved conflicts, moved settings under interrogate section, settings only show if deepbooru flag is enabled
|
3 years ago |
JC-Array
|
963d986396
|
Merge branch 'AUTOMATIC1111:master' into deepdanbooru_pre_process
|
3 years ago |
AUTOMATIC
|
6be32b31d1
|
reports that training with medvram is possible.
|
3 years ago |
|
AUTOMATIC
|
d6fcc6b87b
|
apply lr schedule to hypernets
|
3 years ago |
|
AUTOMATIC1111
|
419e539fe3
|
Merge branch 'learning_rate-scheduling' into learnschedule
|
3 years ago |
|
AUTOMATIC
|
d4ea5f4d86
|
add an option to unload models during hypernetwork training to save VRAM
|
3 years ago |
|
AUTOMATIC
|
6d09b8d1df
|
produce error when training with medvram/lowvram enabled
|
3 years ago |
|
AUTOMATIC1111
|
4f96ffd0b5
|
Merge pull request #2201 from alg-wiki/textual__inversion
Textual Inversion: Preprocess and Training will only pick-up image files instead
|
3 years ago |
|
AUTOMATIC
|
530103b586
|
fixes related to merge
|
3 years ago |
alg-wiki
|
8bacbca0a1
|
Removed my local edits to checkpoint image generation
|
3 years ago |
|
alg-wiki
|
b2368a3bce
|
Switched to exception handling
|
3 years ago |
|
AUTOMATIC
|
5de806184f
|
Merge branch 'master' into hypernetwork-training
|
3 years ago |
|
JC_Array
|
bb932dbf9f
|
added alpha sort and threshold variables to create process method in preprocessing
|
3 years ago |
|
JC-Array
|
47f5e216da
|
Merge branch 'deepdanbooru_pre_process' into master
|
3 years ago |
|
alg-wiki
|
907a88b2d0
|
Added .webp .bmp
|
3 years ago |
Fampai
|
2536ecbb17
|
Refactored learning rate code
|
3 years ago |
alg-wiki
|
f0ab972f85
|
Merge branch 'master' into textual__inversion
|
3 years ago |
|
alg-wiki
|
bc3e183b73
|
Textual Inversion: Preprocess and Training will only pick-up image files
|
3 years ago |
|
alg-wiki
|
7a20f914ed
|
Custom Width and Height
|
3 years ago |
|
alg-wiki
|
6ad3a53e36
|
Fixed progress bar output for epoch
|
3 years ago |
|
alg-wiki
|
ea00c1624b
|
Textual Inversion: Added custom training image size and number of repeats per input image in a single epoch
|
3 years ago |
|
alg-wiki
|
04c745ea4f
|
Custom Width and Height
|
3 years ago |
|
alg-wiki
|
4ee7519fc2
|
Fixed progress bar output for epoch
|
3 years ago |
|
alg-wiki
|
3110f895b2
|
Textual Inversion: Added custom training image size and number of repeats per input image in a single epoch
|
3 years ago |
|
JC_Array
|
1f92336be7
|
refactored the deepbooru module to improve speed on running multiple interogations in a row. Added the option to generate deepbooru tags for textual inversion preproccessing.
|
3 years ago |
|
AUTOMATIC
|
12c4d5c6b5
|
hypernetwork training mk1
|
3 years ago |
Raphael Stoeckli
|
4288e53fc2
|
removed unused import, fixed typo
|
3 years ago |
|
Raphael Stoeckli
|
2499fb4e19
|
Add sanitizer for captions in Textual inversion
|
3 years ago |
|
AUTOMATIC
|
5ef0baf5ea
|
add support for gelbooru tags in filenames for textual inversion
|
3 years ago |
|
AUTOMATIC
|
2865ef4b9a
|
fix broken date in TI
|
3 years ago |
|
AUTOMATIC
|
6785331e22
|
keep textual inversion dataset latents in CPU memory to save a bit of VRAM
|
3 years ago |
|
AUTOMATIC
|
c7543d4940
|
preprocessing for textual inversion added
|
3 years ago |
|
AUTOMATIC
|
a1cde7e646
|
disabled SD model download after multiple complaints
|
3 years ago |
|
AUTOMATIC
|
4ec4af6e0b
|
add checkpoint info to saved embeddings
|
3 years ago |
|
AUTOMATIC
|
71fe7fa49f
|
fix using aaaa-100 embedding when the prompt has aaaa-10000 and you have both aaaa-100 and aaaa-10000 in the directory with embeddings.
|
3 years ago |
|
AUTOMATIC
|
88ec0cf557
|
fix for incorrect embedding token length calculation (will break seeds that use embeddings, you're welcome!)
add option to input initialization text for embeddings
|
3 years ago |
|
AUTOMATIC
|
820f1dc96b
|
initial support for training textual inversion
|
3 years ago |