ESM-IF and ESMFold in the same conda environnment

[Baldwin-disso]

Is it possible to have both ESMFold and ESM-IF working using the same conda environnement ?

I read on the inverse folding page that it should be a separated environnement, but is there a way to do this ?

Here is how I attempted to do this

conda env create -f environment.yml
conda activate esmfold

# install esmfold
pip install "fair-esm[esmfold]"

# OpenFold and its remaining dependency
pip install 'dllogger @ git+https://github.com/NVIDIA/dllogger.git'
pip install 'openfold @ git+https://github.com/aqlaboratory/openfold.git@4b41059694619831a7db195b7e0988fc4ff3a307'

# install pytorch geometric and so on 
pip install pyg_lib torch_scatter torch_sparse torch_cluster torch_spline_conv -f https://data.pyg.org/whl/torch-1.12.1+cu113.html
pip install torch-geometric

# install biotite
pip install biotite

It almost seems to work except for the case where inverse folding is run on cuda indeed.