Revealing my Workflow to Perfect AI Images.

[@sebastiankamph]

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

[@ripleyhrgiger4669]

Your videos are the best guides for generating images using AI models. So clear, well spoken, and the dry humor gets me every damn time. Thanks for taking the time to make these videos for us and to all of the people who make these tools at no charge to us too. I know it's A LOT of work and when I think there aren't good people in the world I remember all of the devs and creators who make content for us at no charge just to share their creations. So thank you so much!

[@sebastiankamph]

Glad to hear you say that and I'm very happy you're enjoying the content :) Hope you'll keep enjoying the videos.

[@Adam-ui8iy]

As an artist, I have sooooooo many reference images that I want to play around this. This is like 100x productivity for artists. Absolutely insane.

[@androidgameplays4every13]

It increased productivity so much that I no longer have the necessity to hire artists, I can create art myself!

[@Cube_Box]

​@@androidgameplays4every13 lmfao I guess that's the art of making money pun intended

[@fancymeai]

You are like the Bob Ross of Stable Diffusion, thank you for showing the workflow!

[@robertmiller32]

LOL i was literally thinking the same thing ..... And here i will generate a happy little tree :)

[@MultiOmega1911]

Umbelievable process, you should do more workflow demonstration as this, it's relaxing asf

[@sebastiankamph]

Thanks, will do! Got a new weekly thing on it

[@TheAiConqueror]

I have to ask Hili directly for the template prompt. I like it! 😁👍

[@sebastiankamph]

He's a man of many talents! 🤩 Thank you 🥰😘

[@iakartuna]

i know your kids are sleeping when you are recording but i also fall asleep when watching your videos. Thanks for the videos.

[@geektoolkit]

Instant subscribe. I've been wathcing numerous videos about how to use stable diffusion but this one was the best explanation, the best techinque, and just flowed so well. Really well done, and super cool image in the end! Thankyou for your work creating this

[@sebastiankamph]

Thank you for taking the time to write such a thoughtful and positive comment. Glad to have you aboard! 😊

[@mariokotlar303]

Thanks that was great!

[@sebastiankamph]

Glad you liked it and thank you for the support, you superstar you! 😊💫💫

[@alexnorth3393]

I liked this. More workflow videos please.

[@adamtubak]

Dude.. i was playing around with sd and mj for half a year now, with more or less efficient workflows and halfway usable results.. but you just opened up my eyes!!

[@sebastiankamph]

Happy it helped you 😊

[@ronaldp7573]

I have learned so much from your channel. I write fiction and now I can bring the characters in my stories to life for my fans.

[@sebastiankamph]

Happy to hear it! 😊🌟

[@beveresmoor]

Finally, I have time to watch your clip again after saving it in my playlist for awhile. This tutorial helps me a lot. ❤

[@sebastiankamph]

Glad it was helpful!

[@lukaz2040]

oh whoah! i've been using Satable Diffusion for months almost daily and I didn't know such a robust workflow! thank you for sharing!

[@sebastiankamph]

Glad it helped! 🌟🤩

[@justinwhite2725]

You have such an old version of auto 1111, so many of those options you've talked about have been renamed or not needed.

[@Smiithrz]

Ah, is that why I don't have the "in-paint at full resolution" checkbox? Was that deprecated for some reason?

[@jessedart9103]

@@Smiithrz On the Inpaint Tab it's now called "Inpaint area -- Only masked"

[@Smiithrz]

@@jessedart9103 Thanks :)

[@audiogus2651]

@@Smiithrz yah I am curious where that went. (Ps. Jesse Dart deleted their comment?)

[@Smiithrz]

@@audiogus2651 oh, weird. He just said it was an old feature, and was replaced with “in-paint only masked” radio button now.

[@untouchedbytime5337]

You're an absolute legend , thanks especially for the free to use base prompts in the description !

[@그래요난-g9y]

Thank you so much! I finally understood how I can improve the quality of my images in stable diffusion. Thank you again!

[@duckcluck123]

I had absolutely no idea you could have so much control over the generated images.

[@thanksfernuthin]

Great stuff. I do most of this already but it's great for people just starting out. When I do the face I set the inpainting canvas size to 1024X1024. A square. Since that better matches the actual area it's working with at that time and it's usually much higher res than the actual image since it's just doing the face. Good job.

[@mangocomputer]

I've been a huge fan of your channel for a while now and truly appreciate the high-quality content you create. It's clear how much effort and passion you put into each video, and that's why I keep coming back! I wanted to share some thoughts on the Patreon model. While I understand the need to support your work, labeling content as "free" while it's locked behind a Patreon subscription feels a bit misleading. I think a lot of us would be more than happy to support you directly if the subscription details were more transparent, showing clearly what's free and what's exclusive to subscribers. Your content is absolutely worth supporting, and with a bit more clarity, I believe many more would be willing to join in on a straightforward subscription basis. Thanks for considering this feedback, and I'm looking forward to your future projects!

[@sebastiankamph]

Thank you for the feedback. The content was initially free, but then I left my job to pursue this. And it's been a real mess to get rid of all the "free".

[@amj2048]

This is a great video, lots of detail, we even get some bonus information about some of the other settings in Automatic 1111. Thanks for making this Sebastian.

[@irangel1958]

Excellent video, I am going to incorporate your workflow into mine. I especially appreciated the side comments on the upscalers. thank you

[@sebastiankamph]

Thank you, glad it was helpful! 🌟

[@sofarsogod]

Amazing to see people who mastered this great tools lml

[@sebastiankamph]

Glad you liked it! 😊

[@rencloudkicker]

FYI, you can manually type in the resolution if the slider bar doesn't give you the number you want.

[@elishmuel1976]

Complete newbie. Started today. I subbed and hope to learn a lot from you, outputting quality, amazing images! Thank you so much for this!

[@sebastiankamph]

Welcome aboard! You joined at a great time. It's easier than ever to create amazing images now. If you need help, hop on the Discord (in channel description).

[@maxmustermann3938]

Some additions: ControlNet also has an inpainting model which can potentially improve results especially with higher denoising. ControlNet + Ultimate SD Upscale can be used together to get some amazing upscaling results. It is somewhat similiar to getting detail by inpainting, but it is automated and controlnet stirs the process to more closely resemble the original image.

[@marcdevinci893]

Thanks so much for sharing this. I learned a ton on how to get hi res results.

[@sebastiankamph]

Glad it was helpful! 🌟🌟🌟

[@marcdevinci893]

@@sebastiankamph So you there's no need to use an inpaint model?

[@SwiteFilms]

Nice Video, very helpful - again! And the beginnings "Hey hey hey" got me as well as the dad joke.

[@sebastiankamph]

Glad you liked it! Thank you for the encouragement 😊

[@KrnelPanc]

I've learned so much from you Sebastian. Also I have a friend from England who is non stop with the dad jokes. You guys might get a long

[@CoconutPete]

Been obsessed with SD for about a month now and if anyone out there is new and has a potato PC, you'll be able to learn faster by using a cloud version vs. trying to run it locally. Otherwise you have to wait for each render to complete before you can learn from your results

[@ComplexTagret]

As usual, very useful tips and tricks! Thanks!

[@WillFalcon]

Where did you get a tab "inpaint at full resolution"? 8:45

[@sebastiankamph]

It's renamed to masked area only

[@justinwhite2725]

You don't need to set the height and weight on control net. That's for the 'create canvas' button. Personally I like 0.8 for the weight to allow some flexibility to the prompt. But honestly even at 0.05 it's great to give the AI a starting point.

[@Repossessionn]

Didnt know the canvas thing! I feel like a moron now constantly changing the height and weight haha

[@sebastiankamph]

Good input! I corrected that in my latest tutorial.

[@justinwhite2725]

@@Repossessionn trust me I used to too until I saw a reply to someone else about it on a discord server.

[@claudianreyn4529]

We will end up with cartoon versions of famous movies or with movies that have totally different actors, or comedy versions of dramas, etc. 😅

[@titusfx]

🎯 Key Takeaways for quick navigation: 00:00 🖼️ Sebastian Kamph shares his advanced workflow for creating high-quality images using Stable Fusion and ControlNet. 01:36 📷 Experiment with different settings, including weight, depth, and model selection, when using ControlNet for image generation. 03:05 🌈 Explore variations in generated images and select the one with the desired composition and color palette. 08:05 🎨 Use image inpainting techniques to enhance specific parts of the generated image, such as faces or details, for better resolution and quality. 10:49 🤖 Experiment with prompts to transform elements of the image, like turning a human into a robot, to create unique and detailed artwork. 12:53 🚀 Combining ControlNet and image inpainting can help you generate high-quality, large images efficiently, improving your AI art workflow.

[@CNC-Time-Lapse]

WOW. This is crazy impressive!

[@sebastiankamph]

Thank you 😊💫

Thanks for showing your workflow. Great video, very informative!

[@sebastiankamph]

Glad you enjoyed it! 🌟

[@teamtwiistz]

Why did you add the prompt at the beginning of the sentence inside brackets? ()

[@sebastiankamph]

That gives it more weight. I'm telling it "This is more important than the rest".

[@abnalfalah]

How do I get styles like the one you use ?

[@sebastiankamph]

Link in video description

[@morganandreason]

Thanks för sharing your process! I've been missing out on the upscaling step you do and have stuck with just hiresfix and img2img, but this will add another dimension if I can find the right upscaler for photorealistic humans.

[@Dre2Dee2]

Excellent, excellent, excellent. This is gonna be great to add to my current workflow, net control seems like such a powerful tool, I think my outputs are gonna be a lot better 😃

[@sebastiankamph]

Glad it was helpful! Have fun and create amazing art 😊

[@andrew_straeker]

Very useful. 👍 I hadn't thought about increasing the resolution progressively with each img2img and/or inpainting step. There is always something to learn. 😸 Thanks 😺👍👍👍

[@sebastiankamph]

Great to hear! 😊💯💫

[@kingkhalagar2836]

Very helpful! It would be great if you went over your extensions you have / recommend too. Like what gives you two styles to pick from instead of 1. I also don't have the "Impaint at full resolution" button etc

[@dmitriykovalenko3507]

Now it's called "Only masked" in group of "Inpaint area"

[@AtaraxiaStorytelling]

amazing run through in this tutorial, so exited to use it.

[@eugeniavorontsova2796]

Just tried this technique. works pretty decent and gives good results overall. Than kyuo so very much for sharing!!!!!!!!!!!

[@sebastiankamph]

I'm glad it helped you. I hope you have lots of fun with it 😊

[@spaceman_the_Australien]

Thankyou for making everything so clear and easy to understand (mostly understood, i.m a Newbie) Liked and Subscribed. 🖖🏻from👽

[@ubassman]

Seb, thank you for this video. I'm just starting out with SD on my Mac Studio M1. So, not as fast as PCs with hot Nvidia cards but still a lot of fun. Keep dropping these videos. I'll keep watching.

[@nigratruo]

How do you get the prompt presets via style that you can chose 2:00 without having to enter all of them by hand? I don't have that in my stable diffusion.

[@sebastiankamph]

See description, it's the free prompt styles.

[@nigratruo]

@@sebastiankamph cool, thank you. I just realized that I'm more looking for a prompt generator that is built in, does that exist? Instead of having to enter all the same terms over and over, there should be a generator that creates the prompt out of selectable text blocks.

[@danielvieira1773]

i dont know why, but i don't got that "inpaint in full res" on my Stable Diffusion.

[@sebastiankamph]

Renamed now, inpaint "masked area only"

[@vanitygamer7817]

so if you had to use contorlnet on the img2img section what would you have done?

[@danielschreiber6342]

Thanks for the clear and concise tutorial. Is it possible to feed controlnet with completely different topics/prompts. Say I want the woman to look like an island from above. How can I archive something like that?

[@Peace_of_Mind]

Awesome, much appreciation

[@SASimulator]

Thank you.. This is so Educational.

[@raihanpurwandaru9483]

Your dad joke got me to chuckle, definitely deserves a like. 😂

[@sebastiankamph]

Hah, glad you liked it 😊💫

[@Proxi_Ex]

More workflow videos of complex put together, high quality images please!

[@LumocolorARTnr1319]

Inpainting will sometimes not use the mask configured if you use Firefox and instead repaint the whole picture no matter what settings you use, don't know why. Opera works though.

[@wernerblahota6055]

Thanks för sharing your process! 👍👍👍

[@TerenceKearns]

Nice one dude. Great information there.

[@sebastiankamph]

Thank you! 😊

[@Artazar777]

Hi, thank you for the awesome video. Can you give me a hint? When you put a mask on the image, how does SD understand what kind of promt to take for this mask, when you have a very large promt?

[@sebastiankamph]

It's tallied together. You can change the weighting by selecting words and do ctrl + arrow up/down.

[@MatichekYoutube]

Hi, can we get a picture link for time stamp 0:14, this style is really nice.

[@타오바오-h8l]

If you already have other photos as jpgs, how do you change the skirts in one photo, and then apply those skirts to the models in the other jpgs?

[@pkay3399]

Thank you. Not sure why it get stuck on "Loading preprocessor: openpose, model". Running Automatic1111 notebook. Everything else works as it should .

[@Mr.BossBaby]

How do we regenerate our current character to be in a different pose without changing the character?

[@EmilioNorrmann]

i which case would be useful to use controlnet while inpainting ?

[@ww-nk6lf]

Awesome video! Can I just ask what's the logic of the prompt (man face 1.4) ? What does the bracket and the 1.4 value do? Put more weighting to the man's face?

[@sebastiankamph]

Yes, more weight!

[@netflixandchinchilla]

What's the benefit of inpainting at higher resolutions vs. doing everything at lower resolution and then upscaling the final image?

[@MonologueMusicals]

at 5:35 you can click into the width value and type 1248 to set it.

[@tat7_gaming.]

i realy like ur vid but i want to know something in my staple diffusion when I send an image to in paint there is no option called full resolution how to activate it ?

[@monbritt]

Hi sebastian, how to make appears the button of inpais fulll resolution?

[@kinggarithos888]

Kids take forever to get to bed it's not just you. Some nights you burn them out and it just makes them crankier, some nights one of them causes problems while the other wants to go to bed. Other nights they pass right out it's really one of the trickiest parts.

[@Jinofcoolnes]

I notice you use euler a in text2img and dpm++ 2m karras img2img. other than stylistic choice, Is there a technical reason behind it? Why no DPM++ 2m karras? Thank you and awesome video!

[@BearDad1994]

Probably just a preference. All of the sampling methods are great in their own way. I personally almost always use Euler A for everything including inpainting. I do enjoy using DPM++ 2m Karras for some things. I did notice when going for skin details such as freckles the DPM++ samplers tend to make round details like freckles more of a line instead of round. At base resolutions it works fine but once you upscale more than 2x it struggles to get the detail I'm looking for personally. Again all preference.

[@Nutronic]

How do we do scribble mode now? The selection above the models selection seems to have disappeared.

[@mr_budo]

I have a problem once I send it to img 2 img and choose SDE karras and generate its giving me totally differnt image nothing close to my base image. I even tried using control net in img to img with same steps and denoising strength as you. But I am not getting as good as your result nothing even close. Am also using same checkpoint. What am I doing wrong ? Any help is highly appricated

[@elsueno3946]

@sebastiankamph, where do i find the free styles? i can only find ones i habe to pay for....

[@Zazume_]

Is it important that the resolution stays at a higher one during the inpainting step? Say I generate a 512x512 image, add details to it by doing the img2img step to 1024x1024. Couldn't I tune the resolution back to 512x512 during the inpainting step (so that the generations of these go A LOT quicker) and then upscale the image back up later, or would I loose details that way?

[@sebastiankamph]

The reason we inpaint at a high resolution is to add more detail. It's not necessary to do this. So you could go lower. But upscaling after won't add detail.

[@baxter987]

Did they remove the "Inpaint at full resolution" option? I no longer see it. Or was the label for that option changed?

[@sebastiankamph]

Inpaint masked only now

[@Mocorn]

Very helpful video right here! It's incredibly helpful to see the whole process in something like this. Thanks =)

[@sebastiankamph]

Glad it was helpful! Thanks for the positive vibes! 😊

[@Aisaaax]

How do you drag your result to inpaint like that? It doesn't work for me at all. I have to open results folder and drag the file.

[@billydakiduk]

Really great and straightforward tutorial - those style prompt presets you mentioned were created by some friends... is there anywhere you'd recommend finding csv files for these. Thanks

[@sebastiankamph]

Yes, come join us on Discord and ask Hili.

[@kopper1956]

You have two drop-downs -- Style 1 and Style 2 -- in the UI. What is this? I have only one.

[@majedmj.digitalworlds]

Hi, I need help please how to save the style…. I am trying it’s not working

[@SilverIlly3]

Hi thanks for the tutorial. I followed it exactly (but with my own picture) but when I inpaint the face I keep getting completely messed up face (4 eyes, 2 noses, distorted mouth etc.). I did upscale of 4 which you said is possible? So working on 2048x3104px but only the face is masked, same settings as you, original etc. Is it because there is a resolution limit or...?

[@SilverIlly3]

@@Forakus so I'm limited to inpainting on 512x512? I cannot upscale first then?

[@danielg123789]

As soon as I get to the inpainting part I run out of vram, I have 12gb of vram so I just assumed I would be fine, my upscaled image is 2048x2048 though so maybe it is just too large? I did only upscale by 2 though, I did notice that 5gb of my vram was being used just running the UI, is there any fix for this or is that just normal?

[@swannschilling474]

Thanks for sharing your workflow! Very helpful!!

[@sebastiankamph]

You're very welcome! 😊😊

[@anagnorisis2024]

i did your tutorial but some of the frames generated include a third or fourth person or even crowds. The first few frames generated are close to the original image. How do you ensure that the frames generated do not include third parties. I usually add negative prompts like 'no third person or crowd'.

[@Smiithrz]

@Sebastian Good dad joke today lol. I have a very similar workflow, but I typically do my upscale on the txt2img side, with Hires Fix, by 2x, using the same seed as the image I like, also with restore faces; then take it to img2img/in-painting. One question I have is; I don’t have that “In-paint at full resolution” checkbox on my A1111, did you enable it somehow? That seems like it would help with some smaller in-paints I try and fail with. Oh, and also a second question... I noticed you're not using an in-painting checkpoint, is protogen simply better?

[@Smiithrz]

nvm on the first Q, @Jesse Dart told me it's now called "Inpaint area -- Only masked". Still curious on Q2, though :)

[@sebastiankamph]

Honestly, I'm very happy with the results I get with the regular protogen, dreamshaper etc. Is it worth the hassle to swap back and forth for inpainting? Maybe, but I'm not seeing it in my workflow right now.

[@Smiithrz]

You seem to get much better results than I do when I try in-painting faces or eyes 🥺

[@MrMe-xs9gq]

[NansException: A tensor with all NaNs was produced in Unet. This could be either because there's not enough precision to represent the picture, or because your video card does not support half type. Try setting the "Upcast cross attention layer to float32" option in Settings > Stable Diffusion or using the --no-half commandline argument to fix this. Use --disable-nan-check commandline argument to disable this check.] I am facing this error can you help? I am running in google colab.

[@GerwaldJensRadsma]

WooOooW gooOOOood workflowwww!

[@sebastiankamph]

Thanks my man! 🌟

[@StrangerCreations352]

How get style 1 and style 2 dropdown menus?

[@beatworldrecords6080]

Your stuff is excellent. Thanks for all you do!

[@sebastiankamph]

I appreciate that! 😊

[@natsharpe4364]

absolute game changer

[@ElHongoVerde]

I love you so much. My wife is jealous right now... I notice that after using an img2img with ControlNet, even if you disable ControlNet to keep working with something else, it will not matter what the prompt say. SD keeps generating images from the original img2img with ControlNet. Is that a bug or I'm doing something wrong? (i bet it's the second option). Thanks a lot for your videos!

[@sebastiankamph]

Haha, thank you! Remember you have both the controlnet input and the img2img input. If one of them is still there, they will influence the output.

[@xaiyeon_xiuzhen]

thank you sir for the amazing workflow walkthrough, it helps a bunch!!

[@FabioHofnik]

Great job! Why Karas?

[@FearfulEntertainment]

I dont have the "inpaint at full resolution" option on my inpaint... Suggestion?

[@sebastiankamph]

They changed the name. It's named "Inpaint area: Only masked" now

[@jon2478]

Question: How did you get 150 tokens? Is it model specific? I only have 75.

[@talessin]

Fantastic work! Thanks! Can you share your styles?

[@sebastiankamph]

Available in Discord

[@talessin]

@@sebastiankamph thx man :)

[@talessin]

@@sebastiankamph Not easy as you said ;) `Can not find any from 30 minuts there :(

[@3dparagon]

Thanks for the video, subbed!

[@itsuki_death]

Great video, do you think it is possible to create a motion in cascadeur and then input it into controlnet to output a video that matches the motion?

[@AIPixelFusion]

could you share your preset style prompts? they look so good!

[@sebastiankamph]

Available on Discord

[@visioncreadora3633]

I could use Stable Diffusion if i have an 8GB RAM PC?

[@sebastiankamph]

It's gpu dependant. 4gb+ vram