bugfix import (#261)

* feature: qwen-image support cpu offload (block) and refactor transfomrer model

* bugfix

* bugfix import

---------
Co-authored-by: Yang Yong(雍洋) <yongyang1030@163.com>

lightx2v/models/networks/qwen_image/model.py

@@ -12,7 +12,6 @@ from .infer.offload.transformer_infer import QwenImageOffloadTransformerInfer
 from .infer.post_infer import QwenImagePostInfer
 from .infer.pre_infer import QwenImagePreInfer
 from .infer.transformer_infer import QwenImageTransformerInfer
-from .transformer_qwenimage import QwenImageTransformer2DModel
 
 
 class QwenImageTransformerModel: