OSError: Can't load tokenizer for 'openai/clip-vit-large-patch14'.

[theshi-1128]

(ls) liu@liu-System-Product-Name:~/ls/ControlNet-main$ python tool_add_control.py ./models/v1-5-pruned.ckpt ./models/control_sd15_ini.ckpt logging improved. No module 'xformers'. Proceeding without it. ControlLDM: Running in eps-prediction mode DiffusionWrapper has 859.52 M params. making attention of type 'vanilla' with 512 in_channels Working with z of shape (1, 4, 32, 32) = 4096 dimensions. making attention of type 'vanilla' with 512 in_channels Traceback (most recent call last): File "/home/liu/ls/ControlNet-main/tool_add_control.py", line 27, in model = create_model(config_path='./models/cldm_v15.yaml') File "/home/liu/ls/ControlNet-main/cldm/model.py", line 26, in create_model model = instantiate_from_config(config.model).cpu() File "/home/liu/ls/ControlNet-main/ldm/util.py", line 79, in instantiate_from_config return get_obj_from_str(config["target"])(**config.get("params", dict())) File "/home/liu/ls/ControlNet-main/cldm/cldm.py", line 311, in init super().init(*args, **kwargs) File "/home/liu/ls/ControlNet-main/ldm/models/diffusion/ddpm.py", line 565, in init self.instantiate_cond_stage(cond_stage_config) File "/home/liu/ls/ControlNet-main/ldm/models/diffusion/ddpm.py", line 632, in instantiate_cond_stage model = instantiate_from_config(config) File "/home/liu/ls/ControlNet-main/ldm/util.py", line 79, in instantiate_from_config return get_obj_from_str(config["target"])(**config.get("params", dict())) File "/home/liu/ls/ControlNet-main/ldm/modules/encoders/modules.py", line 99, in init self.tokenizer = CLIPTokenizer.from_pretrained(version) File "/home/liu/anaconda3/envs/ls/lib/python3.10/site-packages/transformers/tokenization_utils_base.py", line 2029, in from_pretrained raise EnvironmentError( OSError: Can't load tokenizer for 'openai/clip-vit-large-patch14'. If you were trying to load it from 'https://huggingface.co/models', make sure you don't have a local directory with the same name. Otherwise, make sure 'openai/clip-vit-large-patch14' is the correct path to a directory containing all relevant files for a CLIPTokenizer tokenizer.

how can i fix it?

[hxwxss]

Maybe you can download the CLIP-vit-large-patch14 model from Hugging Face and then save it in the path './openai/'.

[theshi-1128]

Thanks a lot for your help！It does work.

发自我的iPhone

------------------ Original ------------------ From: Yuxuan Cheng @.> Date: Sat,Oct 21,2023 6:03 PM To: lllyasviel/ControlNet @.> Cc: theshi-1128 @.>, Author @.> Subject: Re: [lllyasviel/ControlNet] OSError: Can't load tokenizer for'openai/clip-vit-large-patch14'. (Issue #555)

Maybe you can download the CLIP-vit-large-patch14 model from Hugging Face and then save it in the path './openai/'.

— Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: @.***>

[Wei-1989]

Maybe you can download the CLIP-vit-large-patch14 model from Hugging Face and then save it in the path './openai/'.

would you please tell me what models do i need? and should I create a new folder named 'openai' in the root dictory?