search

PKU-YuanGroup / MagicTime

MagicTime: Time-lapse Video Generation Models as Metamorphic Simulators
https://pku-yuangroup.github.io/MagicTime/
Apache License 2.0
1.27k stars 124 forks source link

load text_encoder failed #36

Open coollofty opened 2 weeks ago

coollofty commented 2 weeks ago

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 commented 2 weeks ago

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.