f965a1299f
Fixed Dora implementation. Still highly experimental
Jaret Burkett
2024-02-24 10:26:01 -07:00
1bd94f0f01
Added early DoRA support, but will change shortly. Dont use right now.
Jaret Burkett
2024-02-23 05:55:41 -07:00
9ffa8c3711
Fixed issue when there is no adapter
Jaret Burkett
2024-02-22 02:59:59 -07:00
b68c3ef734
Added te aug adapter
Jaret Burkett
2024-02-21 21:30:26 -07:00
49c41e6a5f
Bug fixes. allow for random negative prompts
Jaret Burkett
2024-02-21 04:51:52 -07:00
2478554c95
Bug fixes. Added IP adapter training for Pixart
Jaret Burkett
2024-02-17 10:06:57 -07:00
93b52932c1
Added training for pixart-a
Jaret Burkett
2024-02-13 16:00:04 -07:00
4ec4025cbb
Added adapter modules for text encoders and direct vision
Jaret Burkett
2024-02-12 08:46:18 -07:00
e074058faa
Work on additional image embedding methods. Finalized zipper resampler. It works amazing
Jaret Burkett
2024-02-10 09:00:05 -07:00
a8481c1670
randomly adjust scale of unconditional noise on ip adapters if training with cfg
Jaret Burkett
2024-02-06 03:44:54 -07:00
e18e0cb5f8
Added comparitive loss when training clip encoder. Allow selecting clip layer. on ip adapter. Improvements to prior prediction
Jaret Burkett
2024-02-05 07:40:03 -07:00
177c7130ec
improved correction of pred norm by targeting the prior
Jaret Burkett
2024-02-01 06:31:04 -07:00
1ae1017748
Bug fixes. added ability to use l1 loss. varous other tests and improvements
Jaret Burkett
2024-01-31 06:30:54 -07:00
92b9c71d44
Many bug fixes. Ip adapter bug fixes. Added noise to unconditional, it works better. added an ilora adapter for 1 shotting LoRAs
Jaret Burkett
2024-01-28 08:20:03 -07:00
f17ad8d794
various bug fixes. Created an contextual alpha mask module to calculate alpha mask
Jaret Burkett
2024-01-18 16:34:27 -07:00
86c70a2a1f
Added an experimental clip fusion model that is showing promise for embedding concepts
Jaret Burkett
2024-01-17 13:13:04 -07:00
655533d4c7
More work on custom adapter
Jaret Burkett
2024-01-16 17:41:26 -07:00
eebd3c8212
Initial training script for photomaker training. Needs a little more work.
Jaret Burkett
2024-01-15 18:46:26 -07:00
5276975fb0
Added additional config options for custom plugins I needed
Jaret Burkett
2024-01-15 08:31:09 -07:00
e190fbaeb8
Prepwork for ilora
Jaret Burkett
2024-01-12 06:41:15 -07:00
290393f7ae
Imporvements to ip weight adaptation. Bug fixes. Added masking to direct guidance loss. Allow importing a file for random triggers. Handle bas meta images with improper sizing.
Jaret Burkett
2024-01-11 12:22:16 -07:00
b2a54c8f36
Added siglip support
Jaret Burkett
2024-01-09 20:52:21 -07:00
b767d29b3c
Adjustments to the clip preprocessor. Allow merging in new weights for ip adapters so you can change the arcitecture while maintaining as much data as possible
Jaret Burkett
2024-01-06 11:56:53 -07:00
645b27f97a
Bug fixes with ip adapter training. Made a clip pre processor that can be trained with ip adapter to help augment the clip input to squeeze in more detail from a larget input. moved clip processing to the dataloader for speed.
Jaret Burkett
2024-01-04 12:59:38 -07:00
65c08b09c3
Added ability to do cfg during training. Various bug fixes
Jaret Burkett
2024-01-02 11:29:57 -07:00
afc231efc1
Added reference adapters, many bug fixes, more ip adapter work and customizability
Jaret Burkett
2024-01-01 17:15:53 -07:00
0892dec4a5
Fixed some new bugs i added. woops
Jaret Burkett
2023-12-28 14:03:42 -07:00
eeee4a1620
Created a size agnostic feature encoder (SAFE) model to be trained in replace of CLIP for ip adapters. It is mostly conv layers so will hopefully be able to handle facial features better than clip can. Also bug fixes
Jaret Burkett
2023-12-28 12:20:27 -07:00
d11ed7f66c
Big fixes and added method to standardize values in both latent and pixel space before feeding into the network. Target values were determined over huge generated regularization sets.
Jaret Burkett
2023-12-26 06:19:48 -07:00
27ad79053e
Added SDXL support for clip vision embedder trainer
Jaret Burkett
2023-12-24 14:31:29 -07:00
05ae95ca89
Added a clip vision adapter trainer. Only works for sd15 for now
Jaret Burkett
2023-12-24 13:26:04 -07:00
0f8daa5612
Bug fixes, work on maing IP adapters more customizable.
Jaret Burkett
2023-12-24 08:32:39 -07:00
7703e3a15e
Fixes for sdxl ip adapter training. Bug fixes
Jaret Burkett
2023-12-21 11:15:58 -07:00
0f597f453e
Switched ip adapter dataloader to clip_image paths so the control paths can be used for training assistant adapters while training ip adapters
Jaret Burkett
2023-12-20 10:32:24 -07:00
dfb64b5957
Allow ip adapters to be much more variable in their creation
Jaret Burkett
2023-12-20 06:18:33 -07:00
82098e5d6e
Added more functionality for ip adapters
Jaret Burkett
2023-12-19 09:54:56 -07:00
b653906715
Fixed ip adapter training. Works now
Jaret Burkett
2023-12-17 08:22:59 -07:00
13d32423f6
Added a polarity balancer to guidance
Jaret Burkett
2023-12-15 15:19:14 -07:00
39870411d8
More guidance work. Improved LoRA module resolver for unet. Added vega mappings and LoRA training for it. Various other bigfixes and changes
Jaret Burkett
2023-12-15 06:02:10 -07:00
e5177833b2
Targeted guidance work
Jaret Burkett
2023-12-09 19:06:18 -07:00
eaa0fb6253
Tons of bug fixes and improvements to special training. Fixed slider training.
Jaret Burkett
2023-12-09 16:38:10 -07:00
bd2bce9b92
Switched to trailing timestep spacing to make timesteps for consistant across schedulers. Honed in on targeted guidance. It is finally perfect. (I think)
Jaret Burkett
2023-11-29 14:32:48 -07:00
93ea955d7c
Added refiner fine tuning. Works, but needs some polish.
Jaret Burkett
2023-11-05 17:15:03 -07:00
8a9e8f708f
Added base for using guidance during training. Still not working right.
Jaret Burkett
2023-11-05 04:03:32 -07:00
d35733ac06
Added support for training ssd-1B. Added support for saving models into diffusers format. We can currently save in safetensors format for ssd-1b, but diffusers cannot load it yet.
Jaret Burkett
2023-11-03 05:01:16 -06:00
ceaf1d9454
Various bug fixes, wip stuff, and tweaks
Jaret Burkett
2023-11-02 18:19:20 -06:00
7d707b2fe6
Added masking to slider training. Something is still weird though
Jaret Burkett
2023-11-01 14:51:29 -06:00
a899ec91c8
Added some split prompting started code, adamw8bit, replacements improving, learnable snr gos. A lot of good stuff.
Jaret Burkett
2023-11-01 06:52:21 -06:00
436a09430e
Added flat snr gamma vs min. Fixes timestep timing
Jaret Burkett
2023-10-29 15:41:55 -06:00
3097865203
Fix llava import.. again
Jaret Burkett
2023-10-29 12:52:17 -06:00
d742792ee4
Fixed issue with not loading short prompt
Jaret Burkett
2023-10-24 16:19:32 -06:00
002279cec3
Allow short and long caption combinations like form the new captioning system. Merge the network into the model before inference and reextract when done. Doubles inference speed on locon models during inference. allow splitting a batch into individual components and run them through alone. Basicallt gradient accumulation with single batch size.
Jaret Burkett
2023-10-24 16:02:07 -06:00
73c8b50975
Added ability to use adagrad from transformers
Jaret Burkett
2023-10-24 11:16:01 -06:00
34eb563d55
Added dataset tagging and management tools using llava
Jaret Burkett
2023-10-24 10:11:47 -06:00
dc36bbb3c8
Added long prompts to general training
Jaret Burkett
2023-10-23 08:12:58 -06:00
9905a1e205
Fixes and longer prompts
Jaret Burkett
2023-10-22 08:57:37 -06:00
d46112a354
Fixes for aug pipeline
Jaret Burkett
2023-10-20 13:24:07 -06:00
07bf7bd7de
Allow augmentations and targeting different loss types fron the config file
Jaret Burkett
2023-10-18 03:04:57 -06:00
da6302ada8
added a method to apply multipliers to noise and latents prior to combining
Jaret Burkett
2023-10-17 06:09:16 -06:00
a05459afaf
Fixed issue with adapters that only had 1 input channel. Added ability to set the percentage chance of adapter matching
Jaret Burkett
2023-10-15 15:13:35 -06:00
Jaret Burkett