Download Prompt styles: www.patreon.com/posts/sebs-hilis-79649068 Please support me on Patreon for early access videos. It will also help me keep creating these guides: www.patreon.com/sebastiankamph
@IIStaffyII
Жыл бұрын
This is the reason that its so important that Stable Diffusion is open source.
@losttoothbrush
Жыл бұрын
I mean its cool yeah, but doesnt it steal art from Artist that way?
@JorgetePanete
Жыл бұрын
it's*
@IIStaffyII
Жыл бұрын
@@losttoothbrush Open source just means people can access the source code and therefore add to the tool. Being open source is not directly contributing to the "stealing" issue. Although indirectly it can make it more accessable. In the end it's a tool and I'd argue what you make with it may be transformative work or not.
@Mimeniia
Жыл бұрын
People "artists" cling to their prompts like their lives depend on it. Asking them to share is like squeazing blood from a stone.
@verendale1789
Жыл бұрын
@@losttoothbrush Well, yknow, if we are gonna steal art, at least make it public and for everyone instead for one big corpo having the goods, hell yea brotha
@daconl
Жыл бұрын
If you want to use the source image as ControlNet image, you don't have to load the ControlNet image separately (it will automatically pick the source image when no image is selected). Saves some time. 🙂
@Naundob
Жыл бұрын
I wonder why img2img is used at all since ControlNet is meant to do the job now instead of the old img2img algorithm, right?
@superresistant0
Жыл бұрын
@@Naundob ControlNet can create from something whereas img2img can create from nothing.
@Naundob
Жыл бұрын
@@superresistant0 Interesting, isn't img2img meant to create a new image from an image instead from nothing?
@daryladhityahenry
Жыл бұрын
Please please please finish these arguments... I don't understand what you both talking about hahaahahah. And give conclusion please. Thanksss
@ikcikor3670
Жыл бұрын
@@Naundob img2img gives you way less control, basically you pick "denoising strength" which at 0.5 basically tells AI "this is a 50% done txt2img image, half way between random noise and desired result, continue working on it until the end" so you have to look for golden middle between your image not changing at all and changing way too much. Controlnet can be used both in txt2img and img2img and it has many powerful features like drawing very accurate poses, keeping lineart intact and turning simple scribbles into actual art (where with normal img2img you'd end up with either an ugly result or one that doesn't resemble the doodle almost at all)
@GrandHorseMusic
Жыл бұрын
Thank you, this is really helpful. My "pencil sketch of a ballerina" had three arms and no head, but eventually I generated something usable. It's all absolutely fascinating and it's been fun to learn over the past week or so.
@sebastiankamph
Жыл бұрын
Glad it was helpful! And we've all struggled with the correct amount of body parts 😅
@VIpown3d
Жыл бұрын
This is the second best thing right after Ikea Köttbullar
@joskimengstrom2853
Жыл бұрын
🐴 🍖
@marcelqueiroz8613
Жыл бұрын
Really cool. Things are evolving pretty fast! Thanks
@sebastiankamph
Жыл бұрын
Right? This is moving extremely fast. I'm hyped for what's more to come! 🌟
@woszkar
Жыл бұрын
This is probably the most useful thing for SD. Thanks for showing us!
@justinwhite2725
Жыл бұрын
This looks amazing. My drive is full but I definitely want to play more with this.
@sebastiankamph
Жыл бұрын
Throw away the other models and get this, it's fantastic! If you only have space for one, get the canny model.
@justinwhite2725
Жыл бұрын
@@sebastiankamph I'm going to get a new hd after work today. 2tb or so. My stable diffusion folder is 500gb. I'm also a little nervous since I have an AMD card I'm not sure if this will work on the CPU, but I'm working on building a new computer soon.
@agusdor1044
Жыл бұрын
This is gold, and Im talking about your video, dude. Really well explained, very detailed, thanks a lot!
@sebastiankamph
Жыл бұрын
Why thank you for the kind words, that's really thoughtful of you 😊🌟
@coloryvr
Жыл бұрын
...WOW! ...the next growth spurt of SD...people say AI makes us stupid but i haven't learned so much since AI crashed into my life...Big FANX for keeping us up to date!
@sebastiankamph
Жыл бұрын
So much new information entering our heads 😅 Thanks for the support! 🌟
@conorstewart2214
Жыл бұрын
AI does and will make people stupid, in the sense they don’t need to learn anything themselves they just ask an AI to do it for them. You are learning because you are interested in it and it is new, once it becomes more prevalent it will most likely stop being open source and people will just be interested in the results, not how it works.
@coloryvr
Жыл бұрын
I agree with many things and I think that children should not have access to generative AIs until a certain age ((16?). However, I have no idea how to remove open source software from millions of private PCs (?). My biggest concern is that the AIs will greatly increase the general smartphone addiction. (I don't have one myself and don't want one either). But: I love "painting" and filming in VR... and thanks to the new AIs, I now have the potential of an entire animation studio at my own disposal.... BTW: The absolute nightmare are AIs that develop weapons, toxins, etc. as well as the AI-based mind-reading technology that is already pushing onto the markets...
@rayamc607
Жыл бұрын
Be so much better when somebody actually puts a proper UI on all of this.
@Jaxs_Time
Жыл бұрын
Brah, your camera is so nice..... Love to see the commitment to your craft. Keep it up fam
@MaxWeir
Жыл бұрын
I had Pingu vibes at the end, this is quite an amazing update.
@dommyshan
Жыл бұрын
That is really awesome :D Gonna try the scribble! I've been having horrible varied results of deformed humans and I was getting sick of it. Haven't touched SD since. Now this changes! :D
@jonathaningram8157
Жыл бұрын
I'm convinced the future of IA generated picture will be with a mix of 3D models. Like you do a precise pose in 3D and apply stable diffusion on it so that it can have precise informations about depth in the scene and that will achieve true photorealistic render.
@martiddy
Жыл бұрын
You can do that already with ControlNet
@nackedgrils9302
Жыл бұрын
Thanks for sharing your experience! I'd kind of given up on SD because my computer is way too slow (5-10min to generate a 512x512 Euler a image) but when I came back to the community last week, everyone was creaming their panties over Controlnet and I had no idea why. Thanks to your explanation, now I kind of understand but I guess I'll have to try it myself some day once I can afford a better computer.
@sebastiankamph
Жыл бұрын
I feel you! But yeah, ControlNet is WILD!
@EmanueleDelFio
Жыл бұрын
Thanks Seb ! you are my Obiwan Kenobi of ai !
@sebastiankamph
Жыл бұрын
Thank you as always my friend! Your supportive attitude is a national treasure 🌟
@BryGuy_TV
Жыл бұрын
Controlnet is insane. Thanks for the examples
@sebastiankamph
Жыл бұрын
You bet!
@royceahr
Жыл бұрын
Sabastian, I get this error when I tried typing pip install opencv-python 'pip' is not recognized as an internal or external command, operable program or batch file. Any idea what is wrong?
@JesseCotto
6 ай бұрын
If you lower the weight to zero it will cost you and arm and a leg. Brilliant! Thanks for Your Video! Definitely Highly Valuable Content.
@jubb1984
Жыл бұрын
Thanks for this well put together tutorial on how to get it going! This is kinda what i was hoping for, turning my b&w line art into ai generated images =D, lotsa scribbles here i come!
@1salacious
Жыл бұрын
Another good easy to follow tutorial, thanks Seb 👍
@onlyyoucanstopevil9024
Жыл бұрын
GLORY TO A.I REVOLUTION!!!
@fynnjackson2298
Жыл бұрын
For storyboarding this is insane.
@bongkem2723
Жыл бұрын
great video on controlnet man, thanks a lot !!
@sebastiankamph
Жыл бұрын
Glad you liked it!
@noonelivesforever2302
Жыл бұрын
ooohhh someone that explain things like should be done. ty
@sebastiankamph
Жыл бұрын
Thank you, that's very kind 😊🌟
@CoconutPete
7 ай бұрын
having issues with scribble brush color.. seems as if I'm drawing with a white color brush on a white canvas
@robcorrina8897
Жыл бұрын
I had difficulty cutting through the jargon. thanks man.
@sebastiankamph
Жыл бұрын
Glad I could help 😊
@nikkitrucking
Жыл бұрын
I was hoping you'll creating the image from the thumbnail, instead, I got a penguin. lol
@Amelia_PC
Жыл бұрын
After being so disappointed with Pose, I had much better results with Depth. Thanks!
@sebastiankamph
Жыл бұрын
Great to hear!
@CoconutPete
6 ай бұрын
controlnet is amazing.. still trying to figure out the HED model
@Rundik
Жыл бұрын
Beautiful images in the thumbnail. Crappy pinguin in the actual video
@sebastiankamph
Жыл бұрын
Check my workflow video if you want the thumbnail art.
@JustinMinnaar
Жыл бұрын
Cute. At 10 mins in, note there is an undo button, but no eraser.
@JonatanE
Жыл бұрын
it's important to note that to get this to work you HAVE to use SD 1.5 for now, it's possible to use SD 2.1 but it's not fully compatible for now.
@mindyours752
Жыл бұрын
People at Artstation just watching as their careers fade away.
@Q-Bits8
Жыл бұрын
Can you do a tutorial on how to do this in google colab? My GPU cant handle this
@sasqets
Жыл бұрын
I would also love to know this. I know there's a way, but I'm totally lost on trying to figure this stuff out myself.
@leilagi1345
Жыл бұрын
i would also love it. i cant find any tutorial videos how to do ControlNet in collab in whole youtube.. why nobody shows how to do it. im lost
@TrashMull
6 ай бұрын
Hello Sebastian Kamph, I really like your channel and the way how you talk and make those very comprehensive videos. I learn a lot from you and I thank you very much for that. Pls never change the way of your videos (calm, stabil, precise). Of course I have a question. I am concerned about the pickle files from Illyasviel. Does pickle mean, that it can harm your PC? If yes, what safetensor files can be the alternative? thank you very much and have a nice day. Best Regards
@sebastiankamph
6 ай бұрын
Hey! Thank you! Safetensors are pickle-free and safe, yes. But official files from lllyasviel are safe
@sharadrbhoir
Жыл бұрын
As a Drawing Teacher of having 33 years of experience of teaching school kids how to draw and paint, One thing for sure....AI can not replace human creativity but I must say this will surely help so many people with poor drawing skill to unleash their creative thoughts and imagination! which for a teacher like me gives immense hope of revolution in Arts! Thanks for such an easy and helpful tutorial on this topic!
@mike_lupriger
Жыл бұрын
@@ClanBez Same, I see possibility to work on multiple projects as a designer. Tedious parts of process are getting automated. Super excited keep exploring!! Will get more time for vacation, well I hope!🤞 PS: In my area, high school art teacher is referred to as Drawing teacher and College art teachers are referred to as Art teachers. Yeah it's little weird.
@rushalias8511
Жыл бұрын
honestly refreshing to see some people be so open minded to this. AI art is often viewed as a job killer but i mean honestly speaking look at so many incidents from the past. When digital art first started i'm sure millions of artists who worked hard with paint, and pencils and ink and every other form of real life art, felt threatened by it. Why pay a guy to paint a logo for you, when you can use a paint tool? Among so many other stuff. But look what happened now, digital art is so common now because its quicker, cheaper and more flexible. If you made a mistake in a real life painting, you didn't have an undo button or an eraser. Just like digital art gave so many new individuals a chance to make art, so too is ai, its all on how you use it
@pedrovitor5324
Жыл бұрын
People feel threatened because a lot of artists still lives from comissions (Btw, they aren't wrong for doing that, it's "easy money"). When you're a teacher in an art school it's easy for you to not be threatened by AI art. Don't get me wrong, I'm not here to sound mad or anything, I'm just saying the truth. I agree AI art will revolutionize the way we think about creativity and I also think it won't destroy art (At least not completely), people will still have their community of non AI art. But it's undeniable, AI art has tons of legal issues and the AI is pretty bad right now. Very rarely I wasn't able to spot if an art was AI or not.
@viquietentakelliebe2561
Жыл бұрын
yeah, but it can sure enhance what skill you have yet to acquire or lack the talent for
@lilacbuni
Жыл бұрын
@@viquietentakelliebe2561 How can u enhance a skill ur not practising? drawing a squiggle then letting ai complete the work based off actual artist's work isn't YOUR imagination or skill and u still learn nothing. ur not doing any of the work the ai is
@Dessme
Жыл бұрын
The audio is SUPER👌👍
@cassiosiquara
Жыл бұрын
This is absolutely amazing! Thank you so much!! s2
@sebastiankamph
Жыл бұрын
Thank you for the kind words 😊
@Argentuza
Жыл бұрын
You have teached me so much, thank you very much!
@sebastiankamph
Жыл бұрын
Glad to hear that!
@MatthewEverhart
Жыл бұрын
Thank you for the tutorial - I am not getting the two images when I generate from ControlNet - just the one.
@sauce8277
Жыл бұрын
I was so worried at all the sexy ladies until I saw the old man. Appreciate that.
@dustyday837
Жыл бұрын
another great video!
@sebastiankamph
Жыл бұрын
Glad you enjoyed it!
@dhavalpatel3455
Жыл бұрын
Thanks for explaining this.
@Gerard_V
Жыл бұрын
Fantastic! thanks for the tutorial! let's play!
@sebastiankamph
Жыл бұрын
Have fun! Good to see you again Gerard 💫
@wowclassicplus
Жыл бұрын
thanks alot. only works with 1.5 tough. but i found out, so all good:)
@theaiplaybook
Жыл бұрын
How did you do it?
@chariots8x230
Жыл бұрын
Pretty awesome! 😍 Now I’d like to know if there’s a way to apply these poses to our own custom characters, instead of just random characters. 🤔 Is it possible to pose two of our original characters together? Also, it’s nice that we can copy the pose, but can we also copy facial expressions into our characters?
@sebastiankamph
Жыл бұрын
Yes and yes! 🌟 It might be a little tricky to get exactly what you're looking for though, but it is possible. I would inpaint each character separately to get the original features.
@eddybeghennou8682
Жыл бұрын
amazing thanks
@XPuntar
Жыл бұрын
I got an error "RuntimeError: mat1 and mat2 shapes cannot be multiplied (154x1024 and 768x320)" What exactly is wrong there? ... Oh, ... do not use 2.1 model(s) with 1.5 ControlNet! That is why is there an error!
@wombattos
8 ай бұрын
Whenever I try to generate anything with for example img2img, it freezes and the generate button doesn't function anymore. Normal txt2img works just fine.
@DanielS-zq2rr
Жыл бұрын
What GPU do you have? I noticed you generate stuff way faster than I'm able to. Thanks for the tutorial btw
@sebastiankamph
Жыл бұрын
RTX 3080. You're welcome!
@whattheshmitty
Жыл бұрын
I dont know what im doing wrong but ControlNet UI isnt even showing up for me and I get this error. Error loading script: controlnet.py Traceback (most recent call last): File "C:\Stable Diffusion\stable-diffusion-webui\modules\scripts.py", line 195, in load_scripts module = script_loading.load_module(scriptfile.path) File "C:\Stable Diffusion\stable-diffusion-webui\modules\script_loading.py", line 13, in load_module exec(compiled, module.__dict__) File "C:\Stable Diffusion\stable-diffusion-webui\extensions\sd-webui-controlnet\scripts\controlnet.py", line 17, in from modules.ui_components import ToolButton ModuleNotFoundError: No module named 'modules.ui_components'
@chainreadydefinewsresearch7970
Жыл бұрын
I'm having same issue... installed extension, but doesn't show up under text2image or img2img
@whattheshmitty
Жыл бұрын
@chainreadydefinewsresearch7970 kzitem.info/news/bejne/o5WtnZmQm5Z_Zoo I just followed this video for a fresh intall and moved all of my models to the new folder and everything worked fine afterwards.
@DevineTalent
Жыл бұрын
I was interested in the video but can't deal with the mouth clicks, please try to remove them, easily done with Adobe Audition
@XKS99
Жыл бұрын
Is this the minute papers guy?
@ghostsquadme
9 ай бұрын
I would love to see the specific examples in the video thumbnail be reproduced
@3dzmax
Жыл бұрын
Hi, thank you for this, I'm very interested but I can't download your prompt styles, any help ?
@namds3373
Жыл бұрын
amazing video, thanks!
@jzwadlo
Жыл бұрын
Great video thank you brother!
@grillodon
Жыл бұрын
How can I use an alpha of an image to use it for create a new different image? Thx
@Katejsej
Жыл бұрын
The only problem we artists have is that there are people or let's say companies, who sell their AI like Midjourney for money, in that case, it is stolen art. If you just use it for free and sell it for free open source like for everyone, then no one has a problem and it isn't a job killer. I don't know any artists who say it is a job killer, that's nonsense.
@MikkoRantalainen
Жыл бұрын
Some artists have a job where they take customer scribble as input and they create output based on that. They should be afraid of their job security if they cannot adapt. However, if they learn to use these AI tools, they can increase their throughput maybe 10x or 100x. And they can always tune required parts fully manually if they have the skills to draw the whole image - then AI is just work multiplier and they can output higher quality output than competitors without manual skills. However, going full luddite and avoiding use of AI tools is a no-go.
@ohyeah9999
Жыл бұрын
Can you change fashion celebriti?
@larryvw1
Жыл бұрын
how do you choose a specific model to use on your project , where is the model tab
@LeChaunpre
Жыл бұрын
Any clue why the controlnet models takes a while to load for me ? I've had the same issue with safetensors models
@TheFeralBachelor
Жыл бұрын
I am lost at step 1 because of an ID10T error. Where is the extension to download? I found the models OK but don't see a dl for the extension.
@pdealmada
Жыл бұрын
is there a way to clone a object or a person with the background with Inpaint? what would be the prompt ? Ty
@DigitalArt-T
Жыл бұрын
Does this have to be on windows? Can it be installed on Mac?
@jupersonyoung7405
11 ай бұрын
I have a question! AttributeError: 'NoneType' object has no attribute 'shape'--> this error keeps appearing while using controlnet.. can you please tell me how to solve this?
@fenriswolf-always-forward
Жыл бұрын
How did you get the drawing canvas ?
Жыл бұрын
Is the preprocessor always has to match the controlnet model? I was using it with mostly no preprocessor selected and it seems to still work? I thought it's only an optional thing which allows you to create an additional pass.
@thorminator
Жыл бұрын
This is nuts! 🤯
@sebastiankamph
Жыл бұрын
I couldn't agree more 🌟
@paulgomez3318
Жыл бұрын
Thank you for this mate
@sebastiankamph
Жыл бұрын
Happy to help! 🌟
@ArtbyKurtisEdwards
Жыл бұрын
another awesome video. Thanks!
@sebastiankamph
Жыл бұрын
Glad you enjoyed it! 🌟
@pranshumittal3374
Жыл бұрын
How do i copy image as control net input?
@skyra1001
Жыл бұрын
I don't have the refresh models button
@Minimalici0us
Жыл бұрын
Can't wait to pair my 5950X with a RTX 4090 :D
@sebastiankamph
Жыл бұрын
Vroom.
@emmettbrown6418
Жыл бұрын
For the Openpose, is there a way to get the coordinates of the joints in the pose?
@ottaviomazzaretto5686
Жыл бұрын
I am following the tutorial, but why my controlnet is for videos ?
@leilagi1345
Жыл бұрын
HI! Very useful video i got intrigued but how to do it all in Google Colab especially the first steps in "Command Prompt" or cnd, is it possible?
@alanbeckco
Жыл бұрын
How did you get the photos you're using in the thumbnail? Just wondering as the video you're doing doesn't actually have them
@sebastiankamph
Жыл бұрын
Same principle, just using a better prompt and more renders.
@alanbeckco
Жыл бұрын
@@sebastiankamph Nice man. The reason why I am asking is I use to be a dancer and the photo in the middle looks legit like a real photo. I tried following the tutorial but doesn't look like it will work for me as I have the 2019-2020 MacBook pro, I think couple of months later they upgraded the chip :( Would be unreal to have a play around and just see what you can come up with
@光辉-e3c
Жыл бұрын
Thank U
@StefanPerriard
Жыл бұрын
This is truly mind-blowing. Thank you for sharing. What version of Stable Diffusion are you using. 1.5 or 2?
@sebastiankamph
Жыл бұрын
Both! Your Stable diffusion program is not version dependant. It's the actual model .ckpt or .safetensors file that has a version. 1.5 is great for illustrations, while 2.1 does a great job with photorealistic portraits.
@sarathdasari9203
Жыл бұрын
Could do also provide guides of installations for MacOS as well?!!
@alexryberg5946
Жыл бұрын
perhaps a bit late but diffusionbee, it just got it all
@jaeyang306
Жыл бұрын
Does this work on macbook pro m2 max? I haven’t seen any tutorials about control net installation on macbook. If you could find a way somehow and upload a guide, this will save so many of us mac users.
@marvinmetan452
11 ай бұрын
It says "pip" is not recognized as command, what to do
@SoaresPatrick
Жыл бұрын
I've done all steps, but the generated image doesn't seems to follow the pose. Any help?
@VTsimpingSan
Жыл бұрын
I don't have the Refresh button. Did they remove it??? D:
@Aerogelatina
Жыл бұрын
Can some one tell me why my canny image (black and white sketch) doesn't show? I can't find an answer.
@jongallivan7164
Жыл бұрын
i am suuuper new to stable diffusion and when i go to the link provided for control net i also see .yaml files what are those and are they needed?
@wernerblahota6055
11 ай бұрын
Thanks for this well put together tutorial on how to get it going!👍👍👍👍👍
@שלוםלוי-ג2נ
Жыл бұрын
First of all, this is amazing!! Second, I do not see the second image of the controlnet-sketch, can someone help?
@_LeThaiAn
Жыл бұрын
my Stable diffusion dont have Extensions tab what should i do
@sebastiankamph
Жыл бұрын
Make sure you have latest version of automatic1111
@RubyRluu
Жыл бұрын
is it necessary to install opencv-python? what is it does?
@JeremyFry
Жыл бұрын
I haven’t been able to get the model to deviate like in your thumbnail. How did you manage to lose the skirt in one photo but get a flowing dress in another? Photoshopping the image fist?
@sebastiankamph
Жыл бұрын
These are not shopped at all, just prompt and settings changed inside SD. You can finetune with both denoising strength and ControlNet weight 🌟
@JeremyFry
Жыл бұрын
@@sebastiankamph I thought you might need to tweak the input images. I'm watching your other workflow videos now and it's been very helpful to see how you can tweak things. Thank you for all these videos!
@blackvx
Жыл бұрын
At this pace, soon we will just have to think about an image and poof!
@sebastiankamph
Жыл бұрын
😅
@mexmax1657
9 ай бұрын
This doesn't work for me sadly. I just get random pictures and no sketches of it
@pkay3399
Жыл бұрын
Thank you. If we are running it on Colab Notebook with WebUI enabled, can we paste the models in Google Drive's Models folder instead of the WebUI folder and then just paste the path into the Notebook?
@SilasGrieves
Жыл бұрын
Not OP but yes, you can copy/paste the models into your folder on your Google Drive but make sure you paste them to the Models folder in the Extensions parent folder and Stable Diffusion’s base models folder.
@pkay3399
Жыл бұрын
@@SilasGrieves Thank you
@gszeman
Жыл бұрын
Issue: When I try to generate after adding the "ballerina dancing in a colorful space nebula, swirling with saturated colors" it generates up to about 94% and then stops without actually generating an image. Any idea what I could be doing wrong?
@messer_sorgivo
Жыл бұрын
Super useful tutorial. I have one question, my stable diffusion does not show me Scribble mode next to enable, i have invert input color, rgb to bgr, low vram and guess mode, why is that?
Пікірлер: 506