Ultimate RunPod Tutorial For Stable Diffusion - Automatic1111 - Data Transfers, Extensions, CivitAI

SECourses Discord To Get Full Support ⤵️

0:00 Intro
2:34 How to deploy a pod - start a server for Stable Diffusion 1.5 Automatic1111 Web UI
3:30 How to select deployment template for Stable Diffusion Web UI in RunPod
4:00 Explanation of temporary disk and persistent volume
4:44 Explanation of credit spending per minute for storage usage in RunPod
8:10 My Pods section
8:30 Connect to the started Pod
8:41 Start SD 2.1 Version Web UI Pod
9:25 Why pick a lesser used Pod
13:11 Where and how to see scheduled maintenance
13:31 Stop Pod vs Terminate (delete) Pod
14:24 Where to see logs to debug and understand errors
15:08 Connect your Pod via a Jupyter Lab interface
15:16 How to change Automatic1111 Web UI command line arguments and restart it
17:54 First prompt in RunPod Automatic1111 Web UI
18:45 Where to see logs, find error logs, debug them
19:35 How to install DreamBooth extension of Automatic1111 Web UI
20:58 Where the generated images are saved
21:10 How to download generated images
21:38 How to update installed extensions
21:55 How to notice port error and fix it
23:04 How to install runpodctl latest version to transfer files very quickly between Pods and PC
23:55 How to download a ckpt file very fast from Hugging Face repo
25:10 Start DreamBooth training with best model and settings
30:41 How to upload your training dataset images
34:15 How to upload thousands of images (big data) from your computer to RunPod via runpodctl
34:28 How to install RunPodCTL on your Windows computer
35:06 How to send files from your PC to RunPod via runpodctl
39:38 Where to find generated checkpoints and sample images during DreamBooth training
41:30 How to delete non-empty folder
41:51 Even though xformers not selected during training, still breaks training and how to fix it
42:29 How to download a folder from RunPod to your PC via runpodctl very quickly
43:09 How to add runpodctl to environment path to use from every folder
47:25 How to continue/resume DreamBooth training
48:20 Test all training checkpoints with x/y plot to find best one
52:09 How to set correct command line arguments for SD 2.1
52:55 Where to see currently spent credits per hour
54:05 How to do DreamBooth training on SD 2.1 - 768 pixel version with best possible settings
57:42 How to generate classification images manually very fast
1:00:26 Why SD 1.5 is superior to 2.1
1:04:34 How to download custom models very fast from CivitAI
1:08:45 How to do Textual Inversion training with some optimal settings
1:13:00 Where Textual Inversion training samples and checkpoints are saved
1:14:07 How to use Textual Inversion check points
1:15:55 Move generated SD 2.1 classification images into correct folder
1:19:26 How to install and run ControlNet extension on RunPod IO
1:21:11 How to download your trained model files (ckpt) into your PC very fast via runpodctl
1:25:00 How to upgrade xformers to 0.0.17 for DreamBooth SD 2.1 training
1:26:04 How to expand runtime disk space
1:27:21 Best settings for SD 2.1 with xformers
1:31:30 What is Stable Diffusion fine tuning and how to do fine tuning with DreamBooth
1:39:20 Best settings quick recap for SD 2.1 for 24 GB VRAM
1:40:34 How to install and run Kohya GUI on RunPod
1:44:16 How to enable public Gradio link for Kohya GUI
1:44:52 How to start RunPods without GPU
1:46:53 Cloud snyching your Pod data / content

thumbnail freepik macrovector

[SECourses]

Please join discord, mention me and ask me any questions. Thank you for like, subscribe, share and Patreon support. I am open to private consulting with Patreon subscription.

[KhanhDuongNguyen]

Your channel is one of the most helpful channels in this area. I suggest all my friends subscribe to your channel when they start learning to use SD.

[TRSPSSER]

U are working until night thanks for your hard working Mr Gözükara

[theeddytor]

i want to cry 😢 thank you so much i have system but it's 2015 tbh i make my monthly income on it using my editing skills but i want to make my own personal project and for that i need high end pc but right now i can't put that much money in system.
but i can pay small amount for using online system. so this is a god's gift for me.

[xt]

so much awesome content, please continue leading and sharing the cutting edge

[raduandreicosmin]

Awesome tutorial, I was really struggling to set up auto1111 with a cloud provider until I found this video

[thinhnguyensb]

I signed up for runpod through your referral link, thanks for your dedication

[herecomesyouknowwho]

Thanks! So much helpful info here that I would never have figured out on my own!

[ArtisteImprevisible]

Brother your channel is amazing, i wish you the best ! 🙏

[armageddon]

very complete.does foocus also run on runpod?

[nomorejustice]

you are amazing man, thanks for the hard work!!!

[magejoshplays]

How interesting, i've had a little trouble when i was overtraining textual inversion embeddings at first but i've got almost 2 dozen done in the last 2 weeks of faces in runpod a1111 using xformers, no half, and precision full together.

[TheHDMICable]

This video is really well made, thanks for your work!

[rupakbiswas]

Great efforts you have put into this video. Thank you.

[MichelHabib]

that's quite some effort, really appreciate it 😍

[gianlucanicolasburcheri]

I have a question.

Suppose that within A1111 I have several things configured.
For example, the form or folders where my images will be saved, what these images will be called, etc. How can I always have that configuration, without having to do everything from scratch?
I assume that most likely I need to download a file into the Stable Diffusion folders, which holds all the configurations, and every time I start the pod, replace that same file, and then restart the program.
Would it be that way?

[jreenhanced]

Amazing!! watching this now. Would you recommend this over colabs? for someone who uses SD heavily and does not have an Nvidia GPU?

[SandroGiambra]

👏👏👏 very very very useful video, thanks for all the details and steps. I haven't tried it yet but I've already seen how to activate and train the dreambooth is explained; I've never been able to on runpod until now.
Thank you and I venture a request:
I hope that in the next videos you can deal with Kohya's stable diffusion gui and Lora extraction because I haven't found indications that work.

[josemuanespinto]

Hi @SECourses, thank you for the video. Wow, this is a lot of information, and I'm not prepared to absorb so much knowledge that is outside my area of ​​expertise, but I'm going to watch the video, as we say, in "pills" that is to say little by little.

[leorene]

Hi ! Tanks a lot for your content . Do you thinks is it possible to mix dreambooth with inpanting please ?