TypeError: AutoencoderKL.__init__() missing 1 required positional argument: 'lossconfig'

Hi,

Recently I delete venv folder to make fresh new install for Comfyui. I git pull all to latest version and start jumping into issue.
- Windows 11
- Comfyui latest
- Python 3.10.11
- Torch 2.1.1cu121

So far it raises bug like following when loading checkpoint node or vae node. I use default workflow to test and still face with issue. Anyone face with same issue can help? Thanks so much.

!!! Exception during processing !!!
Traceback (most recent call last):
File "E:\1.ext_tools\ComfyUI\execution.py", line 151, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
File "E:\1.ext_tools\ComfyUI\execution.py", line 81, in get_output_data
return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True)
File "E:\1.ext_tools\ComfyUI\execution.py", line 74, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
File "E:\1.ext_tools\ComfyUI\nodes.py", line 541, in load_checkpoint
out = comfy.sd.load_checkpoint_guess_config(ckpt_path, output_vae=True, output_clip=True, embedding_directory=folder_paths.get_folder_paths("embeddings"))
File "E:\1.ext_tools\ComfyUI\comfy\sd.py", line 528, in load_checkpoint_guess_config
vae = VAE(sd=vae_sd)
File "E:\1.ext_tools\ComfyUI\comfy\sd.py", line 222, in __init__
self.first_stage_model = AutoencoderKL(ddconfig=ddconfig, embed_dim=4)
TypeError: AutoencoderKL.__init__() missing 1 required positional argument: 'lossconfig'