Mirrored_Repos/InvokeAI
1
0
Fork 0
mirror of https://github.com/invoke-ai/InvokeAI synced 2024-08-30 20:32:17 +00:00
Code Issues Packages Projects Releases Wiki Activity

yet more install clarification

Browse Source
This commit is contained in:
Lincoln Stein 2022-08-16 21:53:07 -04:00
parent 09032fb79d
commit 3f5d39a597
1 changed files with 5 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
README.md
View File

@ -65,10 +65,11 @@ initialization, stable-diffusion tries to download the Bert tokenizer
model from huggingface.co. This obviously didn't work for me.
Rather than set up a hugging face local hub, I found the most
expedient thing to do was to download the Bert tokenizer in advance,
and patch stable-diffusion to read it from the local disk. After you
have completed the conda environment creation and activation steps,the
steps to preload the Bert model are:
expedient thing to do was to download the Bert tokenizer in advance
from a machine that had internet access (in this case, the head node
of the cluster), and patch stable-diffusion to read it from the local
disk. After you have completed the conda environment creation and
activation steps,the steps to preload the Bert model are:
~~~~
(ldm) ~/stable-diffusion$ mkdir ./models/bert