 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 |
|
|
Jaret Burkett
|
dd889086f4
|
Updates to the docker file for jupyterlab
|
2024-09-21 12:07:07 -06:00 |
|
|
Jaret Burkett
|
d97c55cd96
|
Updated requirements to lock version of albucore, which had breaking changes.
|
2024-09-21 11:19:13 -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
|
5c8fcc8a4e
|
Fix bug with zeroing out gradients when accumulating
|
2024-09-03 08:29:15 -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
|
7ed8c51f20
|
Readme cleanup
|
2024-09-01 07:06:09 -06:00 |
|
|
Jaret Burkett
|
6df33156f0
|
Add information about specific weight targeting in the README
|
2024-09-01 06:59:47 -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 |
|
|
Jaret Burkett
|
b322d05fa3
|
Added tutorial link to readme
|
2024-08-22 16:25:32 -06:00 |
|
|
Jaret Burkett
|
8577849eeb
|
Fixed wrong discord link. Woops.
|
2024-08-22 14:49:03 -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
|
e07a98a50c
|
Bugfixes for full finetuning at bf16
|
2024-08-22 05:15:33 -06:00 |
|
|
Jaret Burkett
|
6a754b2710
|
Merge branch 'main' of github.com:ostris/ai-toolkit
|
2024-08-22 04:36:50 -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
|
169dbd22ba
|
Finaized bug reports
|
2024-08-18 16:21:48 -06:00 |
|
|
Jaret Burkett
|
6e7d721382
|
More issues testing
|
2024-08-18 16:20:08 -06:00 |
|
|
Jaret Burkett
|
dc6f36cd82
|
Testing github bug reporting stuff
|
2024-08-18 16:09:52 -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
|
77ee7090e8
|
Update FAQ.md
|
2024-08-18 09:26:22 -06:00 |
|
|
Jaret Burkett
|
078396ceac
|
Added a basic FAQ
|
2024-08-18 09:21:51 -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
|
165510ace2
|
Dumb typo
|
2024-08-15 12:59:32 -06:00 |
|
|
Jaret Burkett
|
0355662e8e
|
Added support for polarity guidance for flow matching models
|
2024-08-15 12:22:00 -06:00 |
|
|
Jaret Burkett
|
b99d36dfdb
|
fixed issue with batch sizes larget than 1
|
2024-08-15 12:21:38 -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
|
e07bf11727
|
Merge pull request #61 from fofr/patch-1
Fix image name in captions section of README
|
2024-08-14 08:01:51 -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
|
465bc1e2f8
|
Update readme again
|
2024-08-13 13:37:22 -06:00 |
|
|
Jaret Burkett
|
0beca0d4a7
|
Updated readme
|
2024-08-13 13:35:20 -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
|
89d61a3b8e
|
Readme updates
|
2024-08-11 13:23:57 -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
|
f8f0657b68
|
Added a colab notebook for training flux loras
|
2024-08-11 12:27:40 -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
|
8d48ad4e85
|
fixed bug I added to demo config
|
2024-08-11 10:28:39 -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
|
fa02e774b0
|
Added info about datset
|
2024-08-10 15:08:05 -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 |
|
|
Jaret Burkett
|
99f24cfb0c
|
Added a conversion script to convert my loras to peft format for flux
|
2024-08-05 14:54:10 -06:00 |
|
|
Jaret Burkett
|
187663ab55
|
Use peft format for flux loras so they are compatible with diffusers. allow loading an assistant lora
|
2024-08-05 14:34:37 -06:00 |
|
|
Jaret Burkett
|
edb7e827ee
|
Adjusted flow matching so target noise multiplier works properly with it.
|
2024-08-05 11:40:05 -06:00 |
|
|
Jaret Burkett
|
0ea27011d5
|
Bug fix
|
2024-08-04 11:07:19 -06:00 |
|
|
Jaret Burkett
|
f321de7bdb
|
Setup to retrain guidance embedding for flux. Use defualt timestep distribution for flux
|
2024-08-04 10:37:23 -06:00 |
|
|
Jaret Burkett
|
88acc28d7f
|
Prep for runpod docker
|
2024-08-03 12:41:06 -06:00 |
|
|
Jaret Burkett
|
de2da96a81
|
Updat4ed requirements
|
2024-08-03 09:50:18 -06:00 |
|
|
Jaret Burkett
|
9beea1c268
|
Flux training should work now... maybe
|
2024-08-03 09:17:34 -06:00 |
|
|
Jaret Burkett
|
369aa143bc
|
Only train a few blocks on flux (for now)
|
2024-08-03 07:02:27 -06:00 |
|
|
Jaret Burkett
|
87ba867fdc
|
Added flux training. Still a WIP. Wont train right without rectified flow working right
|
2024-08-02 15:00:30 -06:00 |
|
|
Jaret Burkett
|
03613c523f
|
Bugfixes and cleanup
|
2024-08-01 11:45:12 -06:00 |
|
|
Jaret Burkett
|
47744373f2
|
Change img multiplier math
|
2024-07-30 11:33:41 -06:00 |
|
|
Jaret Burkett
|
443c996e7f
|
Do a noisy unconsitional for vision direct
|
2024-07-29 15:42:26 -06:00 |
|
|
Jaret Burkett
|
8f0f467c20
|
Switch back to old ilora
|
2024-07-29 07:22:05 -06:00 |
|
|
Jaret Burkett
|
e81e19fd0f
|
Added target_norm_std which is a game changer
|
2024-07-28 16:08:33 -06:00 |
|
|
Jaret Burkett
|
0bc4d555c7
|
A lot of pixart sigma training tweaks
|
2024-07-28 11:23:18 -06:00 |
|
|
Jaret Burkett
|
80aa2dbb80
|
New image generation img2img. various tweaks and fixes
|
2024-07-24 04:13:41 -06:00 |
|
|
Jaret Burkett
|
8d799031cf
|
Remove reg as prior pred
|
2024-07-21 02:34:12 -06:00 |
|
|
Jaret Burkett
|
6e92922c14
|
Add a mergable linear to the mid of ilora
|
2024-07-20 21:17:53 -06:00 |
|
|
Jaret Burkett
|
c51235c486
|
Fixed misnamed var
|
2024-07-20 23:00:20 +00:00 |
|
|
Jaret Burkett
|
c2c4e8cf34
|
Added ability to target parts of lora for ilora
|
2024-07-20 22:45:52 +00:00 |
|
|
Jaret Burkett
|
4c249cf607
|
Added ilora2
|
2024-07-20 16:40:57 -06:00 |
|
|
Jaret Burkett
|
c2d5f712a3
|
Reworked ilora arch
|
2024-07-20 15:35:59 -06:00 |
|
|
Jaret Burkett
|
22d2f6e28f
|
Fixed issue with grad scaling
|
2024-07-20 08:21:57 -06:00 |
|
|
Jaret Burkett
|
a2301cf28c
|
Amall bug fixes
|
2024-07-18 10:39:55 -06:00 |
|
|
Jaret Burkett
|
11e426fdf1
|
Various features and fixes. Too much brain fog to do a proper description
|
2024-07-18 07:34:14 -06:00 |
|
|
Jaret Burkett
|
58dffd43a8
|
Added caching to image sizes so we dont do it every time.
|
2024-07-15 19:07:41 -06:00 |
|
|
Jaret Burkett
|
e4558dff4b
|
Partial implementation for training auraflow.
|
2024-07-12 12:11:38 -06:00 |
|
|
Jaret Burkett
|
c062b7716c
|
Varous bug fixes
|
2024-07-10 15:20:04 -06:00 |
|
|
Jaret Burkett
|
c008405480
|
Added after model load hook
|
2024-07-09 15:34:48 -06:00 |
|
|
Jaret Burkett
|
93e5df1d59
|
Merge branch 'main' of github.com:ostris/ai-toolkit
|
2024-07-07 07:56:56 -06:00 |
|
|
Jaret Burkett
|
045e4a6e15
|
Save entire pixart model again
|
2024-07-07 07:56:48 -06:00 |
|
|
Jaret Burkett
|
76f225a467
|
Fixed issue with TE adapter caption projection
|
2024-07-06 19:09:58 +00:00 |
|