NOTE: These instuctions are also listed on top of the detect_mem_radedit.py file.
You will need to make some changes in the installed diffusers package to solve some dependency issues.
-
Make sure you have created the conda environment. Assuming the name of your conda environment is
demm2. -
Navigate to
/miniconda3/envs/demm2/lib/python3.10/site-packages/diffusers/__init__.pyand comment out in the following way:from .pipelines import ( AudioPipelineOutput, # ConsistencyModelPipeline, # DanceDiffusionPipeline, ... )
-
Navigate to
/miniconda3/envs/demm2/lib/python3.10/site-packages/diffusers/pipelines/pipeline_utils.pyand comment out the following line:from transformers.utils import SAFE_WEIGHTS_NAME as TRANSFORMERS_SAFE_WEIGHTS_NAME
-
Navigate to
/miniconda3/envs/demm2/lib/python3.10/site-packages/diffusers/pipelines/__init__.pyand comment out the following lines:from .consistency_models import ConsistencyModelPipeline from .dance_diffusion import DanceDiffusionPipeline
-
Navigate to
/miniconda3/envs/demm2/lib/python3.10/site-packages/diffusers/pipelines/consistency_models/__init__.pyand comment out the following line:from .pipeline_consistency_models import ConsistencyModelPipeline