nodes/edenartlab-sd-lora-trainer
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
298 Commits 4 Branches 0 Tags
fa76a90c39ff4fb3966f306ebfab28cdf5cbb5bb
Commit Graph
298 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
xander fa76a90c39 add workflows 2024-05-14 15:25:35 +02:00
xander 8b3f9a930f rename workflows 2024-05-14 15:24:33 +02:00
xander cfde9e9180 tiny param tweak 2024-05-14 15:23:26 +02:00
xander 4389ae75c8 force quit training after max steps 2024-05-14 15:21:48 +02:00
xander d66863b4cb more cleanup 2024-05-14 15:12:49 +02:00
xander 110ec0df30 fix lora_scale inference validation samples 2024-05-14 14:34:57 +02:00
xander b51727219e cleanup and try to fix last inference step 2024-05-14 11:42:57 +02:00
xander b8fe89e983 fix typo 2024-05-02 17:11:54 +02:00
aiXander e47fcf429e update predict.py 2024-05-02 07:59:13 -07:00
xander fc63399317 updates 2024-05-02 16:53:49 +02:00
xander 0bd26033cd add conv2 to lora layers 2024-04-29 20:12:08 +02:00
xander 7d78a3d76d updates 2024-04-29 19:37:45 +02:00
xander 45e6f50c24 small updates 2024-04-29 12:10:17 +02:00
xander 39ee9c9630 set defaults 2024-04-27 16:47:35 +02:00
xander 24fcc2e791 update defaults 2024-04-26 15:59:18 +02:00
xander 8da2f58c20 everything is working 2024-04-26 14:52:32 +02:00
xander 7d469d843c cleanup and make all this work also for sd15 2024-04-26 14:38:25 +02:00
xander 2e5912f629 improve token regularization 2024-04-26 13:32:01 +02:00
xander 37bcfe61c9 hyperparam tweaks 2024-04-26 08:45:29 +02:00
xander af6c4676d5 bugfixes 2024-04-25 21:41:57 +02:00
xander 9ae9bc19d2 mask improvements 2024-04-25 21:21:14 +02:00
xander 7218c7e8c2 more tok reg updates 2024-04-24 17:51:42 +02:00
xander c60f3646fa update tok_reg loss 2024-04-24 16:43:22 +02:00
xander e1b05b1b99 update loss plots, reduce tok_reg value 2024-04-24 14:42:05 +02:00
xander 0a72748da6 update preprocess to work better for 1 img 2024-04-23 16:21:49 +02:00
xander f919e3e7a1 setup experiment run 2024-04-23 04:39:35 +02:00
aiXander d4923ab6d2 tiny typo fix 2024-04-22 19:39:16 -07:00
aiXander d613eff061 more tweaks and cleanup 2024-04-22 19:24:28 -07:00
aiXander b48419247a refactor token regularization 2024-04-22 19:08:36 -07:00
aiXander 4d9f8c2e67 more tweaks 2024-04-22 12:22:20 -07:00
aiXander 34e4bc227c ready for pushing new concept trainer 2024-04-22 12:00:40 -07:00
aiXander c85c45b688 add a few more params to cog input 2024-04-22 11:41:37 -07:00
aiXander d4dbb52f9b add adapter_config.json save 2024-04-22 11:32:46 -07:00
aiXander 784bfbf14f prep for cog push 2024-04-22 11:27:04 -07:00
aiXander 327339ebba prep for cog push 2024-04-22 08:41:00 -07:00
aiXander f2d70b64da add dockerignore 2024-04-22 05:48:19 -07:00
xander 41b7895bff add unet_prodigy_growth_factor 2024-04-22 14:36:04 +02:00
mayukhdeb 5b4020d448 save sd15 models as they're supposed to be saved 2024-04-20 06:21:24 -07:00
aiXander 2633c06a87 update gpt4 model 2024-04-19 07:36:51 -07:00
mayukhdeb a33a33295e never load from disk during training 2024-04-19 05:36:24 -07:00
aiXander 3e44dff1da remove pipe before loading from disk 2024-04-19 05:19:49 -07:00
aiXander b2080da7c8 cleanup checkpoint 2024-04-19 05:08:47 -07:00
aiXander 13733a4f19 Merge branch 'main' of https://github.com/edenartlab/trainer into main 2024-04-19 04:58:09 -07:00
aiXander ccaeab8e71 freeze_ti param, save txt-encoder loras into savetensors file 2024-04-19 04:57:59 -07:00
mayukhdeb b568c0c283 load ;checkpoint from disk once training is complete 2024-04-19 04:55:02 -07:00
mayukhdeb c071905658 black formatting 2024-04-19 02:31:43 -07:00
aiXander d1d8eb125e fix 2024-04-19 01:41:28 -07:00
aiXander ea67904a9a simplify 2024-04-19 01:39:43 -07:00
aiXander 909e1c0b10 update defaults 2024-04-18 09:23:47 -07:00
aiXander d573407319 update default configs 2024-04-18 09:12:56 -07:00