cvlab-columbia / zero123

Zero-1-to-3: Zero-shot One Image to 3D Object (ICCV 2023)

Home Page:https://zero123.cs.columbia.edu/

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

sd basemodel

YuzhiChen001 opened this issue · comments

hello! did you make the zero123 to be a basemodel for stable diffusion and controlnet?
I've seen it on civitai,https://civitai.com/models/231725/stable-zero123.
however,I can't load the model like sd1.5.There is the following error message:
raise RuntimeError('Error(s) in loading state_dict for {}:\n\t{}'.format( RuntimeError: Error(s) in loading state_dict for ControlLDM: size mismatch for model.diffusion_model.input_blocks.0.0.weight: copying a param with shape torch.Size([320, 8, 3, 3]) from checkpoint, the shape in current model is torch.Size([320, 4, 3, 3]).
I will be very happy if I get your answer,thanks.

i got it now.