RomanNum3ral
/
ai-toolkit
mirror of https://github.com/ostris/ai-toolkit.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
ai-toolkit/toolkit/models
History
Jaret Burkett 5b5aadadb8
Add LTX-2 Support (#644) 
* WIP, adding support for LTX2

* Training on images working

* Fix loading comfy models

* Handle converting and deconverting lora so it matches original format

* Reworked ui to habdle ltx and propert dataset default overwriting.

* Update the way lokr saves to it is more compatable with comfy

* Audio loading and synchronization/resampling is working

* Add audio to training. Does it work? Maybe, still testing.

* Fixed fps default issue for sound

* Have ui set fps for accurate audio mapping on ltx

* Added audio procession options to the ui for ltx

* Clean up requirements
 		2026-01-13 04:55:30 -07:00
..
loaders Switch to unified text encoder for wan models. Pred for 2.2 14b 2025-08-14 10:07:18 -06:00
wan21 Fix check for making sure vae is on the right device. 2025-10-21 14:49:20 -06:00
DoRA.py WIP - adding support for flux DoRA and ip adapter training 2024-08-22 04:36:39 -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 Add LTX-2 Support (#644) 2026-01-13 04:55:30 -07:00
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 Add stepped loss type 2025-09-22 15:50:12 -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 Add LTX-2 Support (#644) 2026-01-13 04:55:30 -07:00
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
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
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