You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Hey, I have an issue when trying to use the clip-vit-large-patch14.bin clip vision, locally I can use clip-vit-large-patch14.safetensors but it's not supported here. Has anyone managed to get the FLUX IP Adapter working using the cog-comfyui? The error for the .bin version is:
--- cut ---
"exception_message": "Weights only load failed. In PyTorch 2.6, we changed the default value of the weights_only argument in torch.load from False to True.
--- cut ---
I tried other ip adapters but got other errors related to mismatched tensor sizes, so I experimented with the adapter input image sizes - haven't changed anything.
Any ideas?
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
Uh oh!
There was an error while loading. Please reload this page.
-
Hey, I have an issue when trying to use the clip-vit-large-patch14.bin clip vision, locally I can use clip-vit-large-patch14.safetensors but it's not supported here. Has anyone managed to get the FLUX IP Adapter working using the cog-comfyui? The error for the .bin version is:
--- cut ---
"exception_message": "Weights only load failed. In PyTorch 2.6, we changed the default value of the
weights_onlyargument intorch.loadfromFalsetoTrue.--- cut ---
I tried other ip adapters but got other errors related to mismatched tensor sizes, so I experimented with the adapter input image sizes - haven't changed anything.
Any ideas?
Beta Was this translation helpful? Give feedback.
All reactions