Tensors must have same number of dimensions: got 4 and 3
Controlnet at the moment only works for 1.5 models. You are not able to use 2.1 models with Controlnet. You get this error if you try.
cuDNN error: CUDNN_STATUS_INTERNAL_ERROR (Cuda Error)
Out of memory error. This could be because you are using too much VRAM for your server. Either reduce your settings (resolution especially!) or step up to a larger server.
"Aria2c": executable file not found in $PATH)
Make sure you are following the download instructions on the Creator's Club Documentation page. You are not using the correct URL.
Bad Gateway Error or Server won't launch
If you get a black screen, but the timer frame and file browser still stays there you may have a "Bad Gateway". If you highlight the black portion of the screen you will see those words! There are generally three causes of Bad Gateway errors:
- Out of storage. Check your account in the top right of the Smart Timer and see how much storage you are using. If you are over 100GB you will need to delete some models or other files until it is below 100GB. Try to keep some room free at all times.
- Installing an Extension. When you install an extension and then refresh your UI, you will get a bad gateway error. Hit refresh on your browser after a minute and see if the UI loads. Note some extensions take longer to get out of a "Bad Gateway" state.
- Extension problem or misconfiguration. If you are trying different extensions, settings, scripts or VAE, you may find you get a bad gateway on boot. This can be fixed by either deleting the offending file if you know it, or by resetting to back up. To reset to backup, use file browser to rename your "Auto1111" folder to Auto111.bak - Then close down and start a new session. This will make another Auto1111 folder and should boot as normal. Then transfer over anything you need from the .bak folder and delete it.
"In Queue" error
This is the result of trying to do too many things at once! The GPU can only handle one instruction at a time from Automatic1111. You may have a stuck process, or may have accidentally clicked a button when you thought it was non responsive. Either try to interrupt / cancel until the Queue disappears, or restart the session. The logs folder / file can help as well to see if there is a process currently being worked by the GPU.
A common source of this problem is changing the model, then trying to generate an image. Loading a model into the VRAM takes a bit of time, so images can only be generated once it has loaded.
No executable batch size found, reached zero.
This is a Dreambooth out of memory error. Reduce your settings or use a larger server. More information on batch sizes and settings can be found in our Dreambooth documentation.