CogVideoTextEncode: 'SD1Tokenizer' object has no attribute 't5xxl'
File "/home/user/app/custom_nodes/ComfyUI-CogVideoXWrapper/nodes.py", line 169, in process clip.tokenizer.t5xxl.pad_to_max_length = True AttributeError: 'SD1Tokenizer' object has no attribute 't5xxl'
Is this caused by worng t5 model? I used one from: https://huggingface.co/JulesGo/t5-v1_1-xxl-fp8_text_encoder_2
Can you post your workflow (either a good screenshot or the json)? The fact that it's mentioning SD1 in the error makes me suspect that you have the wrong type selected in the Load CLIP node (should be SD3).
@aetherwu Hi, please check your 'Load CLIP' node and make sure you have a t5xxl selected as clip_name. I had the same error message as you and that's how I fixed it.
I have this error and I am using t5xxl_fp8_e4m3fn.safetensors
I have this error and I am using t5xxl_fp8_e4m3fn.safetensors
![]()
Gotta select SD3 as the model type for the clip loader