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

Update probe to always use cpu for loading models

Browse Source
This commit is contained in:
brandonrising 2024-04-03 15:13:25 -04:00 committed by psychedelicious
parent 216b34ac44
commit 51ca59c088
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
invokeai/backend/model_manager/probe.py
View File

@ -324,7 +324,7 @@ class ModelProbe(object):
with SilenceWarnings():
if model_path.suffix.endswith((".ckpt", ".pt", ".pth", ".bin")):
cls._scan_model(model_path.name, model_path)
model = torch.load(model_path)
model = torch.load(model_path, map_location="cpu")
assert isinstance(model, dict)
return model
else: