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

toolkit/stable_diffusion_model.py

@@ -223,6 +223,11 @@ class StableDiffusion:
         self.has_multiple_control_images = False
         # do not resize control images
         self.use_raw_control_images = False
+        # defines if the model supports model paths. Only some will
+        self.supports_model_paths = False
+          
+        # use new lokr format (default false for old models for backwards compatibility)
+        self.use_old_lokr_format = True
         
     # properties for old arch for backwards compatibility
     @property