Add support for training LTX 2.3 (#745)

* Initial support for ltx 2.3. Still needs a lot of testing to make sure it is all right.

* bump version

* Handle lora renaming keys for new ltx 2.3 layers

extensions_built_in/diffusion_models/__init__.py

@@ -7,7 +7,7 @@ from .wan22 import Wan225bModel, Wan2214bModel, Wan2214bI2VModel
 from .qwen_image import QwenImageModel, QwenImageEditModel, QwenImageEditPlusModel
 from .flux2 import Flux2Model, Flux2Klein4BModel, Flux2Klein9BModel
 from .z_image import ZImageModel
-from .ltx2 import LTX2Model
+from .ltx2 import LTX2Model, LTX23Model
 from .zeta_chroma import ZetaChromaModel
 
 AI_TOOLKIT_MODELS = [
@@ -28,6 +28,7 @@ AI_TOOLKIT_MODELS = [
     Flux2Model,
     ZImageModel,
     LTX2Model,
+    LTX23Model,
     Flux2Klein4BModel,
     Flux2Klein9BModel,
     ZetaChromaModel,