-
Notifications
You must be signed in to change notification settings - Fork 553
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Ubuntu Running Error #187
Comments
There is a problem with your model path,You need to copy the model path you downloaded to the local system and replace "training_models/sd_v1–5_vae.ckpt"
|
it means absolute path? |
I solve this with absolute path . but There was torch.cuda.OutOfMemoryError |
|
try rebooting and then start training, but don't run anything else. kill any processes that might be running on the GPU. command |
I killed all other process before run, but it occured out of memories. +-----------------------------------------------------------------------------+ +-----------------------------------------------------------------------------+ |
Here's my output for the 3090. The only thing i can see is that you are running an older driver that only supports up to CUDA 11.4
below is my env listing for running this repo using
|
There was similar issue on comvis |
I have it running on a 3090 and 4090 without problems. Mostly training on SD1.5 based models, 512x512. I don't use the GPU to drive the display or graphics. |
I installed joepenna dream booth on ubuntu. And run following this .
But There is a error
Exception(f"Model Path Not Found : '{self.model_path}'.")
folder name was correct and ckpt file was in it.
Can you help me?
The text was updated successfully, but these errors were encountered: