nodes/kijai-ComfyUI-FluxTrainer
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
136 Commits 4 Branches 0 Tags
a549df730f7d3e5ecb5f95a225b200a654829ca0
Commit Graph
100 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
kijai a549df730f better caption check 2024-09-16 10:10:35 +03:00
kijai 0419754233 Update train_network.py 2024-09-14 09:21:17 +03:00
kijai 3274cd0574 Update flux_lora_train_example01.json 2024-09-12 11:24:18 +03:00
kijai 608073d244 Update lora_flux.py 2024-09-11 02:19:20 +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 1d2e4c225f bugfix 2024-09-09 00:36:21 +03:00
kijai 2c41f44ef0 Merge branch 'train_t5' 2024-09-08 23:31:29 +03:00
kijai 54d8a4b60d fix example 2024-09-08 23:08:57 +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 95de0cbcc9 allow loading models saved in Comfy 2024-09-08 15:57:45 +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 77587e0193 cpu_offload_checkpointing 2024-09-05 16:17:11 +03:00
kijai 0d1d93931f cpu_offload_checkpointing 2024-09-05 15:58:17 +03:00
kijai ba58d55a6c create comfy lora dir if it doesn't exist 2024-09-05 04:19:34 +03:00
kijai 201891ef88 Update nodes.py 2024-09-05 04:18:56 +03:00
kijai a4d2f7545b Update flux_train_utils.py 2024-09-04 19:42:30 +03:00
kijai 721dfc94f3 Update lora_flux.py 2024-09-04 18:59:23 +03:00
kijai 38d3d9ddf6 initial T5 training 2024-09-04 18:50:27 +03:00
kijai 638076f337 Update requirements.txt 2024-09-04 13:57:53 +03:00
kijai 372787dfb6 Add Lion optimizers 2024-09-02 22:33:16 +03:00
kijai 16464ff1ba fix flux_shift 2024-09-01 18:46:45 +03:00
kijai 19a77d835f Use relative nework module import to avoid conflicts 2024-09-01 18:42:18 +03:00
kijai 8d19121517 possible resume fix 2024-09-01 16:19:17 +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 2e745a2612 Update requirements.txt 2024-08-30 16:08:30 +03:00
Jukka Seppänen 72959ea936 Update README.md 2024-08-30 12:53:31 +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 aba4a61024 Update train_util.py 2024-08-30 01:44:22 +03:00
kijai fc1f0e59e2 better error for invalid dataset path 2024-08-30 01:36:52 +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
Jukka Seppänen 4b48695ad4 Merge pull request #3 from ComfyNodePRs/publish 
Add Github Action for Publishing to Comfy Registry
 2024-08-28 19:29:05 +03:00
kijai e9beacd83c update workflow 2024-08-28 19:26:48 +03:00
Jukka Seppänen 464ae3b211 Merge pull request #4 from ComfyNodePRs/pyproject 
Add pyproject.toml for Custom Node Registry
 2024-08-28 19:22:53 +03:00
kijai ba47556acb increase possible max_steps 2024-08-28 14:37:31 +03:00
kijai acf864e850 split mode validation fix 2024-08-27 12:58:42 +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
kijai 94eede3dc0 Update nodes.py 2024-08-27 04:40:41 +03:00
kijai 903bf2c300 optimizer configs 2024-08-27 04:30:32 +03:00
kijai ac171cc826 Create flux_train_example_01.png 2024-08-25 21:27:35 +03:00
kijai 319bc46b62 fix 2024-08-25 19:45:48 +03:00
kijai 695887509a fix split mode args 2024-08-25 19:14:46 +03:00
kijai d4c02e82c7 Update nodes.py 2024-08-25 16:19:40 +03:00
kijai dd7d93e1b7 Update nodes.py 2024-08-25 16:17:42 +03:00
kijai e03b35677e expose some more args, add shift -timestep sampling method 
https://github.com/kohya-ss/sd-scripts/commit/72287d39c76176c0e1c16e8da4f5ddc6f94ea7d6
 2024-08-25 14:18:50 +03:00
kijai 3c3121915f fix min_snr_gamma default for the example workflow 2024-08-24 19:22:39 +03:00
kijai 9f52607be1 class_token first instead 2024-08-24 18:48:04 +03:00
kijai ec58e85b11 Update nodes.py 2024-08-24 18:41:12 +03:00
kijai cbc9d004cb Update nodes.py 2024-08-24 13:59:33 +03:00
kijai 09fd5c01e8 update 2024-08-24 13:50:36 +03:00
kijai bfd6cbecd0 Update nodes.py 2024-08-24 13:38:02 +03:00
kijai 048df4e48f Update nodes.py 2024-08-24 13:34:31 +03:00
kijai 289d1e8543 Merge branch 'main' of https://github.com/kijai/ComfyUI-FluxTrainer 2024-08-24 11:47:36 +03:00
kijai 1e20da3eca Add LoRA extraction node 2024-08-24 11:47:34 +03:00
Jukka Seppänen 31ec87455a Update README.md 2024-08-24 02:01:11 +03:00
kijai f5b4f0c965 Update nodes.py 2024-08-24 01:50:45 +03:00
kijai 62c4f92ac3 Update nodes.py 2024-08-24 00:02:53 +03:00
kijai 43d930c462 full fine tune fixes 2024-08-23 21:41:29 +03:00
kijai 88832603f8 fix bug 2024-08-23 20:19:23 +03:00
kijai 1ba1ef0ec1 Update deepspeed_utils.py 2024-08-23 01:39:04 +03:00
kijai 9c4bba839a Update nodes.py 2024-08-23 01:36:25 +03:00
kijai 74d6d35ca1 fixes from upstream 2024-08-22 20:42:19 +03:00
kijai 3829715515 Update train_util.py 2024-08-22 19:45:20 +03:00
kijai 957ac37c5d always add class_token if provided 2024-08-22 19:40:27 +03:00
kijai d1174c95c4 Update nodes.py 2024-08-21 23:08:12 +03:00
Kijai 14b2d50e22 Check output folder before starting and save args as .json there. 2024-08-21 18:40:28 +03:00
Kijai 9444038bda finetune fixes from upstream 2024-08-21 17:21:15 +03:00
Kijai 617c33da0f attn mask bugfix 2024-08-21 16:08:46 +03:00
kijai c715144f4d Merge branch 'main' of https://github.com/kijai/ComfyUI-FluxTrainer 2024-08-21 04:26:27 +03:00
kijai 9f6f596c0d t5_attn_mask update from upstream 2024-08-21 04:26:25 +03:00
Jukka Seppänen 3740dc4339 Update README.md 2024-08-21 03:58:33 +03:00
Jukka Seppänen 2f8b15c864 Update README.md 2024-08-21 03:56:44 +03:00
Jukka Seppänen a21b21f51f Update README.md 2024-08-21 03:50:50 +03:00
kijai e7f91787f6 update workflow, reqs, fix free space check 2024-08-21 03:23:52 +03:00
kijai 4ddfd9f70b fix more imports 2024-08-20 20:53:34 +03:00
kijai c8f2b53bb8 check available diskspace before starting 2024-08-20 20:22:34 +03:00
kijai 9aea8e5137 fix imports 2024-08-20 20:05:24 +03:00
kijai 2011e0924a Update strategy_base.py 2024-08-20 19:59:26 +03:00
kijai a559358ac8 revert to kohya's multires training 2024-08-20 19:52:33 +03:00
kijai 65aa2df52c add CAME 2024-08-20 17:13:54 +03:00
kijai d07378a99d updates 2024-08-20 16:34:46 +03:00