Runpod•2y ago

Cannot start fast stable diffusion notebook

It was fine this morning but now im getting error messages when starting the pod such as invalid username and password. When following the link to the LastBen repo on huggingface it seems to no longer exist.

Solution

Template has been discontinued/abandoned. RunPod should delist it.

Jump to solution

yoadsterOP•7/18/24, 4:24 PM

Pod ID is 9ccqfpgn4lvxlf

Solution

Marcus•7/18/24, 5:01 PM

Template has been discontinued/abandoned. RunPod should delist it.

yoadsterOP•7/18/24, 5:49 PM

ok cheers

UPDS•7/19/24, 8:53 AM

what is the best alternative to fast stable diffusion?

Marcus•7/19/24, 8:55 AM

This one has latest A1111, ControlNet, ADetailer etc

UPDS•7/19/24, 9:26 AM

Is there any faster way? this template is up for 20 minutes and the A1111 port is still not up yet

Marcus•7/19/24, 9:28 AM

It only has to sync first time, doesn't have to sync after that

Marcus•7/19/24, 9:29 AM

I assume you are using network storage?

UPDS•7/19/24, 9:32 AM

actually I don't use network storage. I start all over again every time

Marcus•7/19/24, 9:35 AM

I wonder why its taking so long to sync then.

UPDS•7/19/24, 9:42 AM

I had this problem with other templates as well. for ULTIMATE Stable Diffusion Kohya ComfyUI InvokeAI I had to wait about 30 minutes

Marcus•7/19/24, 9:45 AM

That one has a lot of stuff that nees to be synced, the A1111 only has A1111 and a few extensions, so should not take the same amount of time to sync.

UPDS•7/19/24, 9:46 AM

I try again

Jason•7/19/24, 9:47 AM

Yeah, for the first time sync it will take longer

Jason•7/19/24, 9:47 AM

Next time you load, it will be faster because some of it are installed already

Marcus•7/19/24, 9:48 AM

Its very quick to sync in community cloud, I don't know why secure cloud syncs so slowly even without network storage, thats a mystery to me.

Jason•7/19/24, 9:59 AM

Might be from the filesystem in secure xloud

UPDS•7/19/24, 10:24 AM

i use secure cloud...maybe thats the problem

ricardo_neurona•7/19/24, 2:11 PM

Why??? It was my favourite template!!! How can I train Loras now? I don´t understand why we don´t have any notification weeks before.

Marcus•7/19/24, 2:13 PM

You can use Kohya_ss for training Lora.

Madiator2011•7/19/24, 4:33 PM

Kohya_ss is much better nowdays

Madiator2011•7/19/24, 4:34 PM

for DB would go with #Better EveryDream2trainer - CUDA12

ricardo_neurona•7/20/24, 10:40 AM

Kohya is sooo slow...

Marcus•7/20/24, 10:54 AM

It depends on your settings

MMarcus It depends on your settings

Jason•7/20/24, 11:13 AM

Which top 3 affects the most

Madiator2011•7/20/24, 2:48 PM

Tried EveryDream?

Lalli•7/21/24, 8:14 AM

Pretty annoyed that my favourite template was removed. A1111 Stable Diffusion 1.9.4 is an okay replacement, but does it have any way to see the Python outputs, like you could with Fast Stable Diffusion? There's information in there that I'm just not getting now.

Jason•7/21/24, 8:21 AM

I think you can use jupyter or web cli

Jason•7/21/24, 8:21 AM

To access the logs somewhere inside /workspace

Jason•7/21/24, 8:21 AM

It should be .txt or .log

Marcus•7/21/24, 8:26 AM

I think there is a folder called output within /workspace-stable-diffusion-webui where you can find the output files

LLalli Pretty annoyed that my favourite template was removed. A1111 Stable Diffusion 1....

Madiator2011•7/21/24, 8:35 AM

It does all into is saved to log file

Madiator2011•7/21/24, 8:35 AM

What exacly things you liked about fast SD?

MMarcus This one has latest A1111, ControlNet, ADetailer etc

tomgn2•7/21/24, 8:48 AM

how can i restore Huggingface A1111 backup file with this template?

tomgn2•7/21/24, 9:04 AM

or have any backup/restore method for A1111?

MMarcus I think there is a folder called output within /workspace-stable-diffusion-webui...

Jason•7/21/24, 9:11 AM

Yep there /

Lalli•7/21/24, 9:15 AM

Yeah, I've found the logs, it'll do.

Madiator2011•7/21/24, 9:19 AM

You probably need restore backup manually

MMadiator2011 What exacly things you liked about fast SD?

Lalli•7/21/24, 9:22 AM

I'm sure it all depends on what you're used to. But I had the scripts customized to my liking and it was nice to have everything I needed (except the webui itself) in that one Jupyter window. The community template just feels cumbersome by comparison.

Madiator2011•7/21/24, 9:23 AM

What exacly customized?

Ttomgn2 how can i restore Huggingface A1111 backup file with this template?

Marcus•7/21/24, 3:19 PM

https://github.com/ashleykleynhans/a1111-huggingface-sync

GitHub

GitHub - ashleykleynhans/a1111-huggingface-sync: Synchronises A1111...

Synchronises A1111 models with a Huggingface repository - ashleykleynhans/a1111-huggingface-sync

MMadiator2011 What exacly customized?

Lalli•7/22/24, 6:05 PM

Just little things like turning on xformers (for which I now have to manually go into the files each time I start a new pod) and automatically downloading all my go-to models. (The download script still works, but now I have to go out of my way to run that, while it was previously part of the start-up script.) None of it really matters, it’s just mildly annoying.

Madiator2011•7/22/24, 6:07 PM

My template has xformers preinstalled and you can store models on NS

Lalli•7/22/24, 6:08 PM

I could've sworn I had issues until I manually enabled xformers, but maybe I broke something when starting it up.

Jason•7/22/24, 6:14 PM

Why use xformers

Madiator2011•7/22/24, 6:54 PM

It's depends on template

Marcus•7/22/24, 8:55 PM

The A1111 template above also has xformers installed already so you don't need to install it unless you installed an extension that broke everything

Marcus•7/22/24, 8:56 PM

A1111 extensions can sometimes be like Crowdstrike, but breaking A1111 installations instead of Windows machines