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

extensions_built_in/diffusion_models/__init__.py

@@ -7,6 +7,7 @@ from .wan22 import Wan225bModel, Wan2214bModel, Wan2214bI2VModel
 from .qwen_image import QwenImageModel, QwenImageEditModel, QwenImageEditPlusModel
 from .flux2 import Flux2Model
 from .z_image import ZImageModel
+from .ltx2 import LTX2Model
 
 AI_TOOLKIT_MODELS = [
     # put a list of models here
@@ -25,4 +26,5 @@ AI_TOOLKIT_MODELS = [
     QwenImageEditPlusModel,
     Flux2Model,
     ZImageModel,
+    LTX2Model,
 ]