Zero

Results 91 comments of Zero

You fixed it? Same here.

> > > an update will be pushed soon. It is already created but needs to be finalized Great!

> Hi @ZeroCool22! Thanks for the bug report. I could not reproduce it, which makes me think it may be related to RAM memory. I see you have 32 GB...

No help? I really want to use IPFS... :(

> What is the default agreement with github when a person create an account and a repository here? Maybe Automatic1111 is already fine and if he adds some license it...

> 11.8 isn't currently supported, you might try an older CUDA library version I'd go with 11.6 or earlier. ![Screenshot_5](https://user-images.githubusercontent.com/13344308/194459511-b7c55c88-9ffa-4324-96d1-016082c7d55f.jpg) Same error and i'm on **11.7**: ![Screenshot_6](https://user-images.githubusercontent.com/13344308/194459839-791769ab-023b-4b40-a344-0d2d10a2f58e.jpg) - `diffusers` version:...

@brentjohnston What GPU you have and what you selected on **accelerate config** when asking [**NO/fp16/bf16**]? **PD:** I tried different selections but nothing changed.

> 11.8 isn't currently supported, you might try an older CUDA library version I'd go with 11.6 or earlier. Can confirm that with **CUDA 11.6** it works, at least with...

> port LD_LIBRARY_PATH=/usr/lib/wsl/lib:$LD_LIBRARY_PATH Correct, this was the main cause, not the CUDA version. The **export LD_LIBRARY_PATH=/usr/lib/wsl/lib:$LD_LIBRARY_PATH** need to be in the config of the train file. Even if you reboot,...