cannot import name 'CLIPTextModelWithProjection' from 'transformers' by running python scripts/txt2img.py --prompt "a photograph of an astronaut riding a horse" --plms

[KRIShark]

I installd using conda env create -f environment.yaml conda activate ldm

The installation was successful. All the packages' ware installed. after it I started the command

python scripts/txt2img.py --prompt "a photograph of an astronaut riding a horse" --plms

and got the error:

(ldm) K:\ImageAI\stable-diffusion>python scripts/txt2img.py --prompt "a photograph of an astronaut riding a horse" --plms Traceback (most recent call last): File "scripts/txt2img.py", line 21, in <module> from diffusers.pipelines.stable_diffusion.safety_checker import StableDiffusionSafetyChecker File "K:\anaconda\envs\ldm\lib\site-packages\diffusers\__init__.py", line 38, in <module> from .models import ( File "K:\anaconda\envs\ldm\lib\site-packages\diffusers\models\__init__.py", line 20, in <module> from .autoencoder_asym_kl import AsymmetricAutoencoderKL File "K:\anaconda\envs\ldm\lib\site-packages\diffusers\models\autoencoder_asym_kl.py", line 21, in <module> from .autoencoder_kl import AutoencoderKLOutput File "K:\anaconda\envs\ldm\lib\site-packages\diffusers\models\autoencoder_kl.py", line 21, in <module> from ..loaders import FromOriginalVAEMixin File "K:\anaconda\envs\ldm\lib\site-packages\diffusers\loaders.py", line 45, in <module> from transformers import CLIPTextModel, CLIPTextModelWithProjection, PreTrainedModel, PreTrainedTokenizer ImportError: cannot import name 'CLIPTextModelWithProjection' from 'transformers' (K:\anaconda\envs\ldm\lib\site-packages\transformers\__init__.py)

How to fix it?

[CHNAICORP]

I installd using conda env create -f environment.yaml conda activate ldm

The installation was successful. All the packages' ware installed. after it I started the command

python scripts/txt2img.py --prompt "a photograph of an astronaut riding a horse" --plms

and got the error:

(ldm) K:\ImageAI\stable-diffusion>python scripts/txt2img.py --prompt "a photograph of an astronaut riding a horse" --plms Traceback (most recent call last): File "scripts/txt2img.py", line 21, in <module> from diffusers.pipelines.stable_diffusion.safety_checker import StableDiffusionSafetyChecker File "K:\anaconda\envs\ldm\lib\site-packages\diffusers\__init__.py", line 38, in <module> from .models import ( File "K:\anaconda\envs\ldm\lib\site-packages\diffusers\models\__init__.py", line 20, in <module> from .autoencoder_asym_kl import AsymmetricAutoencoderKL File "K:\anaconda\envs\ldm\lib\site-packages\diffusers\models\autoencoder_asym_kl.py", line 21, in <module> from .autoencoder_kl import AutoencoderKLOutput File "K:\anaconda\envs\ldm\lib\site-packages\diffusers\models\autoencoder_kl.py", line 21, in <module> from ..loaders import FromOriginalVAEMixin File "K:\anaconda\envs\ldm\lib\site-packages\diffusers\loaders.py", line 45, in <module> from transformers import CLIPTextModel, CLIPTextModelWithProjection, PreTrainedModel, PreTrainedTokenizer ImportError: cannot import name 'CLIPTextModelWithProjection' from 'transformers' (K:\anaconda\envs\ldm\lib\site-packages\transformers\__init__.py)

How to fix it?

Upgrade your transformers version

1. Uninstall your old transformers version pip uninstall transformers
2. And then. Upgrade transformers version to 4.32.0 pip install transformers==4.32.0
3. That's it.