load text_encoder failed

[coollofty]

text_encoder = CLIPTextModel.from_pretrained(os.path.join(checkpoint_path, 'Magic_Weights'), subfolder="text_encoder").cuda()

get:

!!! Exception during processing !!! F:\ComfyUI\ComfyUI\models\magictime\Magic_Weights does not appear to have a file named text_encoder\config.json

There is no file named 'config. json' in the text_decoder directory

[SHYuanBest]

Thanks for your interest. You need to change 'os.path.join(checkpoint_path, 'Magic_Weights')' to the path of the base model, i.e. sd1.5.