aigc-apps / CogVideoX-Fun

📹 A more flexible CogVideoX that can generate videos at any resolution and creates videos from images.
Apache License 2.0
486 stars 32 forks source link

pop from empty list #73

Open TRONBFFL opened 2 days ago

TRONBFFL commented 2 days ago

Was trying a Lora (maybe I am using the wrong one) but the two I tried received "pop from empty list" error. Thoughts?

I tried these both (BTW the workflow works without using the Lora) https://huggingface.co/DylanDDeng/cogvideo-lora-v1/ https://huggingface.co/ECNU-CILab/ExVideo-CogVideoX-LoRA-129f-v1

Error loading layer !!! Exception during processing !!! pop from empty list Traceback (most recent call last): File "C:\comf2\ComfyUI\custom_nodes\CogVideoX-Fun\cogvideox\utils\lora_utils.py", line 396, in merge_lora curr_layer = curr_layer.getattr(temp_name) File "C:\comf2\venv\lib\site-packages\diffusers\models\modeling_utils.py", line 155, in getattr return super().getattr(name) File "C:\comf2\venv\lib\site-packages\torch\nn\modules\module.py", line 1931, in getattr raise AttributeError( AttributeError: 'CogVideoXTransformer3DModel' object has no attribute 'transformer'