Jaret Burkett
04424fe2d6
Added config setting to set the timestep type
2024-09-24 06:53:59 -06:00
Jaret Burkett
40a8ff5731
Load local hugging face packages for assistant adapter
2024-09-23 10:37:12 -06:00
Jaret Burkett
2776221497
Added option to cache empty prompt or trigger and unload text encoders while training
2024-09-21 20:54:09 -06:00
Jaret Burkett
f85ad452c6
Added initial support for pixtral vision as a vision encoder.
2024-09-21 15:21:14 -06:00
Plat
79b4e04b80
Feat: Wandb logging ( #95 )
...
* wandb logging
* fix: start logging before train loop
* chore: add wandb dir to gitignore
* fix: wrap wandb functions
* fix: forget to send last samples
* chore: use valid type
* chore: use None when not type-checking
* chore: resolved complicated logic
* fix: follow log_every
---------
Co-authored-by: Plat <github@p1at.dev >
Co-authored-by: Jaret Burkett <jaretburkett@gmail.com >
2024-09-19 20:01:01 -06:00
Jaret Burkett
951e223481
Added support to disable single transformers in vision direct adapter
2024-09-11 08:54:51 -06:00
Jaret Burkett
fc34a69bec
Ignore guidance embed when full tuning flux. adjust block scaler to decat to 1.0. Add MLP resampler for reducing vision adapter tokens
2024-09-09 16:24:46 -06:00
Jaret Burkett
279ee65177
Remove block scaler
2024-09-06 08:28:17 -06:00
Jaret Burkett
3a1f464132
Added support for training vision direct weight adapters
2024-09-05 10:11:44 -06:00
Jaret Burkett
121a760c19
Added proper grad accumulation
2024-09-03 07:24:18 -06:00
Jaret Burkett
e5fadddd45
Added ability to do prompt attn masking for flux
2024-09-02 17:29:36 -06:00
Jaret Burkett
d44d4eb61a
Added a new experimental linear weighing technique
2024-09-02 09:22:13 -06:00
Jaret Burkett
7d9ab22405
Rework ip adapter and vision direct adapters to apply to the single transformer blocks even though they are not cross attn.
2024-09-01 10:40:42 -06:00
Jaret Burkett
40f5c59da0
Fixes for training ilora on flux
2024-08-31 16:55:26 -06:00
Jaret Burkett
3e71a99df0
Check for contains only against clean name for lora, not the adjusted one
2024-08-31 07:44:13 -06:00
Jaret Burkett
60232def91
Made peleminary arch for flux ip adapter training
2024-08-28 08:55:39 -06:00
Jaret Burkett
3843e0d148
Added support for vision direct adapter for flux
2024-08-26 16:27:28 -06:00
liaoliaojun
e127c079da
fix: print out the path where the image encode failed ( #107 )
2024-08-22 21:34:35 -06:00
martintomov
34db804c76
Modal cloud training support, fixed typo in toolkit/scheduler.py, Schnell training support for Colab, issue #92 , issue #114 ( #115 )
...
* issue #76 , load_checkpoint_and_dispatch() 'force_hooks'
https://github.com/ostris/ai-toolkit/issues/76
* RunPod cloud config
https://github.com/ostris/ai-toolkit/issues/90
* change 2x A40 to 1x A40 and price per hour
referring to https://github.com/ostris/ai-toolkit/issues/90#issuecomment-2294894929
* include missed FLUX.1-schnell setup guide in last commit
* huggingface-cli login required auth
* #92 peft, #114 colab, schnell training in colab
* modal cloud - run_modal.py and .yaml configs
* run_modal.py mount path example
* modal_examples renamed to modal
* Training in Modal README.md setup guide
* rename run command in title for consistency
2024-08-22 21:25:44 -06:00
apolinário
4d35a29c97
Add push_to_hub to the trainer ( #109 )
...
* add push_to_hub
* fix indentation
* indent again
* model_config
* allow samples to not exist
* repo creation fix
* dont show empty [] if widget doesnt exist
* dont submit the config and optimizer
* Unsafe to have tokens saved in the yaml file
* make sure to catch only the latest samples
* change name to slug
* formatting
* formatting
---------
Co-authored-by: multimodalart <joaopaulo.passos+multimodal@gmail.com >
2024-08-22 21:18:56 -06:00
Jaret Burkett
338c77d677
Fixed breaking change with diffusers. Allow flowmatch on normal stable diffusion models.
2024-08-22 14:36:22 -06:00
Jaret Burkett
a939cf3730
WIP - adding support for flux DoRA and ip adapter training
2024-08-22 04:36:39 -06:00
Jaret Burkett
c45887192a
Unload interum weights when doing multi lora fuse
2024-08-18 09:35:10 -06:00
Jaret Burkett
13a965a26c
Fixed bad key naming on lora fuse I just pushed
2024-08-18 09:33:31 -06:00
Jaret Burkett
f944eeaa4d
Fuse flux schnell assistant adapter in pieces when doing lowvram to drastically speed ip up from minutes to seconds.
2024-08-18 09:09:11 -06:00
Jaret Burkett
81899310f8
Added support for training on flux schnell. Added example config and instructions for training on flux schnell
2024-08-17 06:58:39 -06:00
Jaret Burkett
f9179540d2
Flush after sampling
2024-08-16 17:29:42 -06:00
Jaret Burkett
452e0e286d
For lora assisted training, merge in before quantizing then sample with schnell at -1 weight. Almost doubles training speed with lora adapter.
2024-08-16 17:28:44 -06:00
Jaret Burkett
0355662e8e
Added support for polarity guidance for flow matching models
2024-08-15 12:22:00 -06:00
Jaret Burkett
9001e5c933
Change flux latent spact if so it will not use old cache
2024-08-14 11:27:40 -06:00
Jaret Burkett
7fed4ea761
fixed huge flux training bug. Added ability to use an assistatn lora
2024-08-14 10:14:13 -06:00
Jaret Burkett
00bd3d54a3
Actually use the save dtype from the config file.
2024-08-13 17:08:27 -06:00
Jaret Burkett
f7cf2f866f
Make 100% sure lora alpha matches for flux
2024-08-13 14:24:03 -06:00
Jaret Burkett
418f5f7e8c
Added new experimental time step weighing that should solve a lot of issues with distribution. Updated example. Removed a warning
2024-08-13 12:02:11 -06:00
Jaret Burkett
9ee1ef2a0a
Added experimental modified sigma sqrt weight mapping for linear timestep scheduling for flowmatching
2024-08-12 17:03:09 -06:00
Jaret Burkett
599fafe01f
Allow user to have the full flux checkpoint local
2024-08-12 09:57:16 -06:00
Jaret Burkett
af108bb964
Bug fix with dataloader. Added a flag to completly disable sampling
2024-08-12 09:19:40 -06:00
Jaret Burkett
a6aa4b2c7d
Added ability to set timesteps to linear for flowmatching schedule
2024-08-11 13:06:08 -06:00
Jaret Burkett
7f0ecdb377
Merge branch 'main' of github.com:ostris/ai-toolkit
2024-08-11 11:10:45 -06:00
Jaret Burkett
fbed8568fb
Actually use the correct timestep sampling instead of calculating it and moving on lol. Tested a few with it and it seems to work better.
2024-08-11 11:10:37 -06:00
Jaret Burkett
6d31c6db73
Added a fix for windows dataloader
2024-08-11 10:48:24 -06:00
Jaret Burkett
6490a326e5
Fixed issue for vaes without a shift
2024-08-11 10:30:55 -06:00
Jaret Burkett
ec1ea7aa0e
Added support for training on primary gpu with low_vram flag. Updated example script to remove creepy horse sample at that seed
2024-08-11 09:54:30 -06:00
Jaret Burkett
2308ef2868
Added flux training instructions
2024-08-10 14:10:02 -06:00
Jaret Burkett
b3e03295ad
Reworked flux pred. Again
2024-08-08 13:06:34 -06:00
Jaret Burkett
e69a520616
Reworked timestep distribution on flowmatch sampler when training.
2024-08-08 06:01:45 -06:00
Jaret Burkett
acafe9984f
Adjustments to loading of flux. Added a feedback to ema
2024-08-07 13:17:26 -06:00
Jaret Burkett
653fe60f16
Updates to flow matching algo
2024-08-07 15:04:17 +00:00
Jaret Burkett
c2424087d6
8 bit training working on flux
2024-08-06 11:53:27 -06:00
Jaret Burkett
272c8608c2
Make a CFG version of flux pipeline
2024-08-05 16:35:53 -06:00
