Refactor model loading in generate.py to use dynamic model paths for audio and video components. Simplify weight loading logic in LTX2TextEncoder to accommodate both monolithic and reformatted model structures. Introduce a check for existing model paths in get_model_path function to enhance robustness.

2026-03-09 15:51:21 +01:00
parent d1dd30cbac
commit 9f37dab076
5 changed files with 85 additions and 50 deletions
--- a/mlx_video/components/init.py
+++ b/mlx_video/components/init.py
@@ -0,0 +1,3 @@
+from .smart_turn import Model, ModelConfig
+
+__all__ = ["Model", "ModelConfig"]