Error loading model: 'JC_Models' object has no attribute 'model'

[evanerichards]

I've been using JoyCaption in my workflows for months. I updated in the comfyUI manager and now nothing works. I tried to backtrack, but I can't even get it back to how it was.

When I try to use joy caption it just returns the text "Error loading model: 'JC_Models' object has no attribute 'model'"

My models location hasn't changed so it should be able to find the JoyCaption model, or at very least, it should be able to download it. But it isn't doing either.

Don't know if this info is useful at all:

Python version: 3.12.10 (tags/v3.12.10:0cc8128, Apr 8 2025, 12:21:36) [MSC v.1943 64 bit (AMD64)] pytorch version: 2.7.1+cu118 Set vram state to: NORMAL_VRAM Device: cuda:0 NVIDIA GeForce RTX 3090 : cudaMallocAsync Using pytorch attention ComfyUI version: 0.3.67 ComfyUI frontend version: 1.28.8 Total VRAM 24575 MB, total RAM 65460 MB

[1038lab]

what is your tranformers version and have you install the requirments.txt?

[JemZhu]

Same problem here， reinstalled all the requirments.txt and the problem is still there.