keyerror:no clip_txt_model

[a1122446488]

When I run Python gradio_canny2image.py, keyerror: no clip_txt_model appears. How should I download this

[GaParmar]

Hi,

Could you provide the exact error message that you encountered?

-Gaurav

[a1122446488]

Hello, I'm here https://huggingface.co/stabilityai/sd-turbo/tree/main Download relevant files directly from the website, but encounter these issues during runtime Traceback (most recent call last): Traceback (most recent call last): File "E:\Codes\sc\img2img-turbo-main\img2img-turbo-main\gradio_canny2image.py", line 8, in model = Pix2Pix_Turbo("edge_to_image") File "E:\Codes\sc\img2img-turbo-main\img2img-turbo-main\src\pix2pix_turbo.py", line 31, in init self.tokenizer = AutoTokenizer.from_pretrained("stabilityai/sd-turbo", subfolder="tokenizer") File "C:\ProgramData\anaconda3\envs\img2img-turbo\lib\site-packages\transformers\models\auto\tokenization_auto.py", line 733, in from_pretrained config = AutoConfig.from_pretrained( File "C:\ProgramData\anaconda3\envs\img2img-turbo\lib\site-packages\transformers\models\auto\configuration_auto.py", line 1064, in from_pretrained config_class = CONFIG_MAPPING[config_dict["model_type"]] File "C:\ProgramData\anaconda3\envs\img2img-turbo\lib\site-packages\transformers\models\auto\configuration_auto.py", line 761, in getitem raise KeyError(key) KeyError: 'clip_text_model'

[GaParmar]

It looks like you have some issues with downloading the SD-Turbo model. Could you try deleting the cached sd-turbo model and run these commands to see if it gets downloaded correctly:

from diffusers import AutoencoderKL, UNet2DConditionModel
tokenizer = AutoTokenizer.from_pretrained("stabilityai/sd-turbo", subfolder="tokenizer")

[a1122446488]

Is the download of the SD Tyrbo model from https://huggingface.co/stabilityai/sd-turbo/tree/main Just install all of them directly and create them in the stablityai file?

[GaParmar]

You should not need to download the model manually from the website. The model should get downloaded automatically when you run the command above.

[a1122446488]

But when I run Python graphic_cannoy2image.py without downloading it, Traceback (most recent call last) will appear: File "E:\Codes\sc\img2img-turbo-main\img2img-turbo-main\gradio_canny2image.py", line 8, in model = Pix2Pix_Turbo("edge_to_image") File "E:\Codes\sc\img2img-turbo-main\img2img-turbo-main\src\pix2pix_turbo.py", line 31, in init self.tokenizer = AutoTokenizer.from_pretrained("stabilityai/sd-turbo", subfolder="tokenizer") File "C:\ProgramData\anaconda3\envs\img2img-turbo\lib\site-packages\transformers\models\auto\tokenization_auto.py", line 733, in from_pretrained config = AutoConfig.from_pretrained( File "C:\ProgramData\anaconda3\envs\img2img-turbo\lib\site-packages\transformers\models\auto\configuration_auto.py", line 1048, in from_pretrained config_dict, unused_kwargs = PretrainedConfig.get_config_dict(pretrained_model_name_or_path, kwargs) File "C:\ProgramData\anaconda3\envs\img2img-turbo\lib\site-packages\transformers\configuration_utils.py", line 622, in get_config_dict config_dict, kwargs = cls._get_config_dict(pretrained_model_name_or_path, kwargs) File "C:\ProgramData\anaconda3\envs\img2img-turbo\lib\site-packages\transformers\configuration_utils.py", line 677, in _get_config_dict resolved_config_file = cached_file( File "C:\ProgramData\anaconda3\envs\img2img-turbo\lib\site-packages\transformers\utils\hub.py", line 470, in cached_file raise EnvironmentError( OSError: We couldn't connect to 'https://huggingface.co' to load this file, couldn't find it in the cached files and it looks like stabilityai/sd-turbo is not the path to a directory containing a file named tokenizer\config.json. Checkout your internet connection or see how to run the library in offline mode at 'https://huggingface.co/docs/transformers/installation#offline-mode'.

[GaParmar]

Ah, that is unexpected, maybe you have some network connection issues?

[a1122446488]

So I can just go straight to the https://huggingface.co/stabilityai/sd-turbo/tree/main Is it running after manual installation on?

[GaParmar]

I have not tried using huggingface in offline mode. Maybe this thread might be helpful? https://github.com/huggingface/transformers/issues/11231

[a1122446488]

Okay, I'll give it a try. Thank you very much

[wangwenqiao666]

https://www.cs.cmu.edu/~img2img-turbo/models/sketch_to_image_stochastic_lora.pkl https://www.cs.cmu.edu/~img2img-turbo/models/edge_to_image_loras.pkl download model in ./checkpoints.

[447425299]

Hello, @a1122446488 ， I was wondering if you had managed to resolve the issue mentioned above. If indeed you have, I would greatly appreciate it if you could kindly share the steps you took to arrive at a solution.

Thank you very much for your assistance.

[kanekiCY]

Hello, @a1122446488 ， I was wondering if you had managed to resolve the issue mentioned above. If indeed you have, I would greatly appreciate it if you could kindly share the steps you took to arrive at a solution.

Thank you very much for your assistance.

This problem can be solved by downloading all the files in the SD Turbo directory and organizing them according to the directory format on the webpage.