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/sd_trainer/SDTrainer.py

@@ -859,6 +859,11 @@ class SDTrainer(BaseSDTrainProcess):
                 loss = apply_snr_weight(loss, timesteps, self.sd.noise_scheduler, self.train_config.min_snr_gamma)
 
         loss = loss.mean()
+        
+        # check for audio loss
+        if batch.audio_pred is not None and batch.audio_target is not None:
+            audio_loss = torch.nn.functional.mse_loss(batch.audio_pred.float(), batch.audio_target.float(), reduction="mean")
+            loss = loss + audio_loss
 
         # check for additional losses
         if self.adapter is not None and hasattr(self.adapter, "additional_loss") and self.adapter.additional_loss is not None: