EladWarshawsky
EladWarshawsky
> i fixed it, i needed to install cuda in a different way hey what was the core difference you made?
same issue for me, have to train on cpu, i'd use efficientkan for this. main thing is that the library doesn't have symbolic regression implemented yet.
pip install sync_batchnorm from sync_batchnorm import SynchronizedBatchNorm2d the install works for me, and the import does as well. Haven't tested it with the actual model yet. I'll let you know.
yeah what about sync_batchnorm?
> The documentation says > > ``` > Similarly, if you want to use ControlNet or SDEedit, create a yaml config as in ``config/config_controlnet.yaml > ``` > > Want should...
Thank you! I will try it out :)
Open-Sora already uses a deep compression autoencoder for the backbone of it, enabling the training costs to be pretty low. I'd be interested in hearing what you have in the...
any progress on the controlnet release?
Not to be a bother, but any controlnet updates for sana-sprint?