ai-toolkit/toolkit/models
Jaret Burkett d5612dd35c Adjust the x0 of some DFEs 2026-07-22 10:38:40 -06:00
..
loaders Add sapiens2 matting as a mask generator. Begin transition to model paths and model folders. 2026-05-20 08:56:16 -06:00
v2 Move z_image over to the new modeling class 2026-07-13 17:12:30 -06:00
wan21 Add cached conditioning recovery to wan 22 5b model 2026-07-10 10:22:24 -06:00
DoRA.py Restore device runtime scales for compiled adapters (#963) 2026-07-18 08:19:57 -06:00
FakeVAE.py DEF for fake vae and adjust scaling 2025-09-12 18:09:08 -06:00
LoRAFormer.py Remove ip adapter submodule 2025-04-18 09:59:42 -06:00
RRDB.py Fixed numerous issues with traing ESRGAN 2023-08-08 20:03:19 -06:00
auraflow.py Partial implementation for training auraflow. 2024-07-12 12:11:38 -06:00
autoencoder_tiny_with_pooled_exits.py Improvements to VAE trainer. Allow CLIP loss. 2025-07-24 06:50:56 -06:00
base_model.py Fix issue where the log lone for samples would double up sometimes 2026-07-17 08:11:32 -06:00
block.py Added training for a custom version of ERSGAN arcitecture. Testing training now 2023-08-07 18:04:23 -06:00
clip_fusion.py Work on additional image embedding methods. Finalized zipper resampler. It works amazing 2024-02-10 09:00:05 -07:00
clip_pre_processor.py 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 2024-01-06 11:56:53 -07:00
cogview4.py Added ability to add models to finetune as plugins. Also added flux2 new arch via that method. 2025-03-27 16:07:00 -06:00
control_lora_adapter.py More work on mean flow loss. Moved it to an adapter. Still not functioning properly though. 2025-06-16 07:17:35 -06:00
decorator.py Added training for an experimental decoratgor embedding. Allow for turning off guidance embedding on flux (for unreleased model). Various bug fixes and modifications 2024-12-15 08:59:27 -07:00
diffusion_feature_extraction.py Adjust the x0 of some DFEs 2026-07-22 10:38:40 -06:00
flux.py More work on mean flow loss. Moved it to an adapter. Still not functioning properly though. 2025-06-16 07:17:35 -06:00
flux_sage_attn.py Added support for full finetuning flux with randomized param activation. Examples coming soon 2024-11-21 13:05:32 -07:00
i2v_adapter.py Cleanup 2025-04-18 11:44:49 -06:00
ilora.py Remove ip adapter submodule 2025-04-18 09:59:42 -06:00
ilora2.py Various experiments and minor bug fixes for edge cases 2025-04-25 13:44:38 -06:00
llm_adapter.py Various experiments and minor bug fixes for edge cases 2025-04-25 13:44:38 -06:00
lokr.py Restore device runtime scales for compiled adapters (#963) 2026-07-18 08:19:57 -06:00
mean_flow_adapter.py Work on mean flow. Minor bug fixes. Omnigen improvements 2025-06-26 13:46:20 -06:00
pixtral_vision.py Quick patch to scope xformer imports until a better solution 2024-09-28 15:36:42 -06:00
redux.py Added support for training flux redux adapters 2024-11-21 20:01:52 -07:00
sapiens2.py Add sapiens2 matting as a mask generator. Begin transition to model paths and model folders. 2026-05-20 08:56:16 -06:00
single_value_adapter.py Removed all submodules. Submodule free now, yay. 2025-04-18 10:39:15 -06:00
size_agnostic_feature_encoder.py WIP on SAFE encoder. Work on fp16 training improvements. Various other tweaks and improvements 2024-05-27 10:50:24 -06:00
sref.py Avoid loading state dict for automagic for now until I can sort out some issues 2025-02-26 17:03:14 -07:00
subpixel_adapter.py small bug fixes 2025-03-30 20:09:40 -06:00
te_adapter.py Remove ip adapter submodule 2025-04-18 09:59:42 -06:00
te_aug_adapter.py Remove ip adapter submodule 2025-04-18 09:59:42 -06:00
tipsv2.py Add ability to do hidden states with tipsv2 2026-06-22 11:00:04 -06:00
vd_adapter.py Remove ip adapter submodule 2025-04-18 09:59:42 -06:00
zipper_resampler.py Work on additional image embedding methods. Finalized zipper resampler. It works amazing 2024-02-10 09:00:05 -07:00