kijai
|
6a91611a2b
|
Fix network args, update example folder path to support template loader
|
2025-02-02 16:29:04 +02:00 |
|
kijai
|
f6af45a169
|
update prodigyplusschedulefree, support Flex with arg bypass_flux_guidance
https://github.com/kohya-ss/sd-scripts/pull/1893
|
2025-01-31 21:52:02 +02:00 |
|
kijai
|
998968f5ff
|
Support LyCORIS
https://github.com/KohakuBlueleaf/Lycoris
|
2025-01-16 19:36:18 +02:00 |
|
kijai
|
136697a655
|
Update prodigy-plus-schedule-free
|
2025-01-10 12:12:58 +02:00 |
|
kijai
|
a15cfb181a
|
sd35 support and updates from upstream
|
2024-12-04 12:24:29 +02:00 |
|
kijai
|
3ba4c14e53
|
Updates from upstream: model detection, better full finetune block swap, update prodigyplusschedulefree
|
2024-11-29 13:40:30 +02:00 |
|
kijai
|
b8fe91abdd
|
Expose more options for ProdigyPlusScheduleFree
|
2024-11-21 02:02:38 +02:00 |
|
kijai
|
381b0a4bb1
|
Add ProdigyScheduleFree
https://github.com/LoganBooker/prodigy-plus-schedule-free
for testing
|
2024-11-20 14:38:21 +02:00 |
|
kijai
|
971e1cf553
|
Update nodes.py
|
2024-11-11 11:14:38 +02:00 |
|
kijai
|
a348bae0a2
|
Merge branch 'main' of https://github.com/kijai/ComfyUI-FluxTrainer
|
2024-11-07 00:17:05 +02:00 |
|
kijai
|
8bfe1f668b
|
small fix
|
2024-11-07 00:17:03 +02:00 |
|
Jukka Seppänen
|
f05d2c3c96
|
Merge pull request #74 from chrisgoringe/patch-1
Make FluxTrainEnd an output node
|
2024-10-05 12:36:36 +03:00 |
|
kijai
|
959d434d71
|
Add FluxTrainAndValidateLoop
Single node without preview to run the training and validate at given intervals
|
2024-09-29 01:52:26 +03:00 |
|
chrisgoringe
|
9df7868dc7
|
Make FluxTrainEnd an output node
So that you don't need to use any of the outputs to get the thing to run!
|
2024-09-27 11:28:38 +10:00 |
|
kijai
|
4ad054cce5
|
updates from upstream kohya
|
2024-09-26 18:33:28 +03:00 |
|
kijai
|
f9d3824c8a
|
Add schedulerfree optimizers
|
2024-09-19 16:33:56 +03:00 |
|
kijai
|
de56a60f28
|
better block select
|
2024-09-16 14:47:18 +03:00 |
|
kijai
|
a549df730f
|
better caption check
|
2024-09-16 10:10:35 +03:00 |
|
kijai
|
94ae756b5e
|
add ability to set clip and T5 LR separately
|
2024-09-11 02:06:24 +03:00 |
|
kijai
|
753f617f26
|
save workflow as json first thing as well, allow block ranges for block select
|
2024-09-10 17:05:18 +03:00 |
|
kijai
|
47c62fd8c9
|
Update nodes.py
|
2024-09-10 01:06:54 +03:00 |
|
kijai
|
09a8d7ffca
|
Update nodes.py
|
2024-09-09 22:52:01 +03:00 |
|
kijai
|
c3aa4ea889
|
fix cpu_offload_checkpointing
|
2024-09-09 20:27:31 +03:00 |
|
kijai
|
b52849ad9a
|
Update nodes.py
|
2024-09-09 02:52:15 +03:00 |
|
kijai
|
4cf65f66e2
|
fix validation sampling when training clip_l and caching
|
2024-09-09 01:25:33 +03:00 |
|
kijai
|
c61fcf09cf
|
update examples
|
2024-09-08 23:06:59 +03:00 |
|
kijai
|
66a5fa96c9
|
Update nodes.py
|
2024-09-08 17:48:02 +03:00 |
|
kijai
|
284bb6f112
|
add lora path to load network_weights in the model select node
|
2024-09-08 16:20:40 +03:00 |
|
kijai
|
280f2557b9
|
Update nodes.py
|
2024-09-08 13:11:01 +03:00 |
|
kijai
|
299a994197
|
Update nodes.py
|
2024-09-08 02:56:30 +03:00 |
|
kijai
|
7f486c8916
|
add seed widget to help refresh dataset between runs
|
2024-09-08 02:22:55 +03:00 |
|
kijai
|
712ffb7a1b
|
fix test sampler
|
2024-09-07 23:59:13 +03:00 |
|
kijai
|
1c70cce963
|
support fp8 e5m2
|
2024-09-07 18:27:02 +03:00 |
|
kijai
|
cd8e756103
|
pbar fixes
|
2024-09-07 02:41:09 +03:00 |
|
kijai
|
c6de455381
|
block select
|
2024-09-07 02:15:42 +03:00 |
|
kijai
|
98ca556b23
|
Update nodes.py
|
2024-09-06 21:47:51 +03:00 |
|
Kijai
|
0a720115de
|
update
|
2024-09-06 20:43:40 +03:00 |
|
kijai
|
201891ef88
|
Update nodes.py
|
2024-09-05 04:18:56 +03:00 |
|
kijai
|
38d3d9ddf6
|
initial T5 training
|
2024-09-04 18:50:27 +03:00 |
|
kijai
|
372787dfb6
|
Add Lion optimizers
|
2024-09-02 22:33:16 +03:00 |
|
kijai
|
19a77d835f
|
Use relative nework module import to avoid conflicts
|
2024-09-01 18:42:18 +03:00 |
|
kijai
|
8f6a90e5a9
|
add flux_shift
|
2024-09-01 13:37:13 +03:00 |
|
kijai
|
7095626d6a
|
fix the ability to disable fp8_base
|
2024-08-31 16:50:18 +03:00 |
|
kijai
|
816f0ec75f
|
fix bug with dataset adding stacking
removing a dataset node still won't remove added dataset
|
2024-08-30 03:11:15 +03:00 |
|
kijai
|
4daa4181e7
|
Update nodes.py
|
2024-08-29 13:02:48 +03:00 |
|
kijai
|
66749c8772
|
clip training
|
2024-08-29 12:48:33 +03:00 |
|
kijai
|
ba47556acb
|
increase possible max_steps
|
2024-08-28 14:37:31 +03:00 |
|
kijai
|
794a207aaf
|
Update nodes.py
|
2024-08-27 12:40:09 +03:00 |
|
kijai
|
3437461c93
|
Update nodes.py
|
2024-08-27 12:24:14 +03:00 |
|
kijai
|
07762fb4f0
|
expose mask, resume
resume doesn't seem functional in kohya for Flux yet
|
2024-08-27 12:21:11 +03:00 |
|