Mastering ControlNet on Stable Diffusion: Your Complete Guide
![Vladimir Chopine [GeekatPlay]](http://yt3.ggpht.com/C8QIoKOqO3xNbQhrLw7Q48NVh8ynPa99GNZ2qYvEN4Csg_nwKRnLcMFYfEdljEseP84ZCfUixQ=s48-c-k-c0x00ffffff-no-rj)
ฝัง
- เผยแพร่เมื่อ 23 มิ.ย. 2024
- Take your AI skills to the next level with our complete guide to ControlNet in Stable Diffusion. Elevate your creations today! If you found this video helpful, please like, share, and subscribe for more amazing content.
Git: git-scm.com/
Python: www.python.org/downloads/wind...
ControlNet on github: github.com/lllyasviel/Control...
Controlnet inpaintig model: github.com/mikonvergence/Cont...
ControlNet T2I adapters: huggingface.co/TencentARC/T2I...
ControlNet models: github.com/lllyasviel/Control...
Installing Stable Diffusion: • Personal and uncensore...
Installing OpenGPT: • Free and local ChatGPT...
ControlNet and AI animation: • Next level of AI Anima...
Very impressive AI driving image and video upscale topazlabs.com/ref/1514/ , try for free.
THANK YOU for your support!
Please subscribe and leave your comments, and don't forget to click on the notification bell: “Look daddy, the teacher says, every time a bell rings an angel gets his wings,” ZuZu Bailey from “It's A Wonderful Life.”
What do I use:
Image upscaling topazlabs.com/ref/1514/
Micro SD cards 256Gb V3, I use these in Drones, Insta 360, and GoPro's amzn.to/3HsTU7j
Must have: Micro SD storage/reader/Cables: amzn.to/3GZ33D8
Simplified Photoshop, no annual fees, just one-time purchase amzn.to/3DaUpAi
Canon R5 is not cheap, but it is definitely the best amzn.to/3DclTFX
Must have lens adapter EF to RF amzn.to/3Dk1qhp
Insta 360 X3, I am really impressed by this camera: amzn.to/3HqdMb4
My to-go camera GoPro 11 : amzn.to/3XMcKMc
DJI Osmo 6 amzn.to/3zsKlAG
Portable lights, very versatile usage : amzn.to/3wsUqMa
Another DJI great product. Drone Mini 3 Pro, my togo: amzn.to/3XKN9mG
One of my favorite modifiers from Fotodiox - amzn.to/2Rfr1Px
Another modifier, that helps with fill light - amzn.to/2ReC2jX
Corsair keyboard: amzn.to/3DlclHN
Adobe Photoshop CC - amzn.to/2TNrLwL
My #1 dress in Baroque/Rococo photoshoots. very good quality: amzn.to/401rGHQ
Baroque outfit for males: amzn.to/3kBdEg2
I recommend getting this shirt for the outfit above: amzn.to/3Wzcv5Z
My Vue book - amzn.to/2TGUkvQ
3D Art essentials - amzn.to/2RfqPjh
My Patreon webpage - / geekatplay
Tutorials and packs - gumroad.com/geekatplay
Tutorials website - www.geekatplay.com
Photography - www.chopinephotography.com
Subscribe to my channel for fast notifications on new tutorials - / @geekatplay
00:00 Introduction
01:06 Repository vs Extension
01:44 Installing as extension
03:01 Adding models
04:08 ControlNet settings
06:19 Testing installation
07:07 Open pose preprocessor
09:24 How to select model
13:34 Canny model
15:13 Depth model
16:45 Normal map
17:14 OpenPose model
18:52 MLSD Model
19:23 Lineart model
20:07 SoftEdge model
21:10 Scribble model
22:50 Seg model
23:36 Inpaint model
25:53 T2IA adapters
27:11 ControlNet option and settings
![พบรัก - INK WARUNTORN [Official MV]](http://i.ytimg.com/vi/n2wjOYVC38Y/mqdefault.jpg)
Very nice! Very in depth explanation and comfy to listen to :)
Glad you liked it!
I was wondering why the heck my controlnet was not working with the newest version until I saw your video! Thank you!
THX Vladimir for making this tutorial, much appreciated :)
thanks for your comprehensive explanations
thank you for support!
I Love you Vladimir!! I have learned so much from you! You are truly an amazing artist and teacher and I cant thank you enough!!
Thank you for your thorough explanations! They are excellent.
Glad you like them!
Thank you very much for full tutorial explanations you're doing. It helped me a lot.
You are welcome!
Your video will definitely help a lot.
I hope so!
Hello!
Thank you for your tutorials.
I installed ControlNet automatically, but the folder with the models was empty. Your links were helpful, so I manually saved all the models. However, for some reason, ControlNet doesn't see some SD models (for example, mlsd) and often gives an error: AttributeError: 'NoneType' object has no attribute 'shape'. Do you happen to know how to fix this?
Thank you!
thank you so much
You're welcome! Thank you for your support!!!!!
Thank you for tuto
You're welcome
Thank you for your tutorials. Abo directly, supi.👍👍👍
You are welcome 😊
When i use a pose using open pose my image never follows the pose. Its always random. Any advice?
Hi ! thank you for your work. Any idea why i do not have "config file for controlnet models " and "config file for adapter mofels" options when i'm in controlNet settings ? so i can't change the model when trying usind t2i adapter transfer style. thank you
Auto detected, just put in: \stable-diffusion-webui\extensions\sd-webui-controlnet\models
Hello, could you please provide a tutorial on generating height maps from images using stable diffusion
Can you tell us something about the new SDXL ControlNet models? I am using Deforum and warpFusion but some models do not have an XL version or there are different variations.
Awesome video, thanks!
ControlNet using SD 1.5, i dont think it is working with sdxl models yet, but i need check on that
A tutorial on how to color our own digital drawings would be great :)
Great suggestion!
Any idea why Oppenpose doesn't work for me while all the other control controlnet models do? I can get it to work on Rundiffusion, but not on my local PC, so I don't think it's because I'm using the wrong settings. Ever hear of anyone else having this problem?
Any idea on why ControlNet isn't popping up for me after installing? I know you said that means it's installed incorrectly but every tutorial I checked told me to do exactly what I did
👋
Preprocessor Preview not showing for me even i checked "Allow Preview". What am i missing?
Does anyone know what can be done if the image is looking great until around 70% generation, then it goes weird in the last steps? The pics are looking beautiful until that last part, then it all goes wrong.
Does changing the number of steps work?
Great sharing!
Lots of reasons. Check refiner, upscale, steps and cfg
my python is not working any idea
❤
thank you for your support!
When I find a new model I have started to run a generation with only a negative prompt, and nothing in the positive prompt.
It feels like I 10/9 get big boobs with a girl staring at me.
I want to make situational or slice of life images. But I seem to always get a picture with someone staring at me, and often need to put female body parts in the negative prompt.
I can make a landscape image, building and portrait, but find it difficult to make an image with people not focusing on the camera.
Anyone know of a "ignore camera" lora, or a model good for making scenes rather than portraits?
I wouldnt call this mastering as this feels more like a basic intro. Good video tho!.