Stable Diffusion for Flawless Portraits

[@IAcePTI]

This is the best tutorial i saw about how to use it. Realy great.

[@thays182]

Holy crap this is great. I'm 6 days down the rabbit hole of A1111/Stable Diff and I can't get enough. I've been looking for this exact video! Thank you!

[@jbe8690]

From an art point of view/perspective, Vlad is the best A.I. mentor on KZbin, by far.

[@Geekatplay]

Thank you for your support!

[@jbe8690]

His equivalency to A.I. art is of Da Vinci modern age. Imagine if Vlad lived in Da Vinci's time. 🤔

[@jbe8690]

@@Geekatplay I just now looked up a KZbin video about stable diffusion, and brought me back here brother. The algorithm knows where to take me for education. Its so good.

[@luclenders]

This could save the trouble of training models for different faces. Very helpfull! thanks

[@Geekatplay]

Absolutely!

[@mdahsenmirza2536]

THANK YOU!!, That face trick has been something I've been trying out for months, now I can better make portraits!!

[@Geekatplay]

Great to hear!

[@CreativePunk5555]

This is an amazing workflow Vladimir, great job! So many people fighting to get exactly this for so long. Again, great job!

[@Geekatplay]

thank you

[@半生轻狂客-阿美莉卡]

牛逼！！？ 你太厉害了。我研究了半天，看到你这个视频我终于学会了。谢谢你。👍🏻👍🏻👍🏻👍🏻👍🏻👍🏻👍🏻👍🏻👍🏻👍🏻👍🏻

[@Geekatplay]

thank you!

[@ObaedaKorani]

Thank you my friend

[@vitim1979]

Владимир спасибо большое. Отличный тутониал. Буду пробовать что то похожее

[@Geekatplay]

Spasibo!

[@ИльяДедов-и4ъ]

Хоть ролик и пошаговая инструкция к портретам, у вас получилось мимоходом объяснить работу многих параметров. Спасибо за видос.

[@shirekerling5151]

Hello, great video. However, I'm not sure how you got the ControlNet section there and the models? Can you add an explanation for that? There are many results when searching for it and in the link you provided and there is no explanation about that. Thank you.

[@dreamzdziner8484]

Such a great trick.❤ Watching these vids makes me realize that I'm still a noob when it comes to SD. 😉

[@rpgecho]

Wow, this is amazing! I updated the Civitai page to announce that I started training RPG V5.0. I will ship that version with a set of Control Net image to help people have more control on the model.

[@Geekatplay]

thank you

[@toddaway]

Very cool, and helpful! Have you figured out a way to make the in-painted face match the style of the rest of the picture?

[@cryptojedii]

Yes...using Affinity Photo you can do just that!

[@tamroberts7303]

Could do another img2img on low denosing with the controlnet.

[@tstone9151]

@@cryptojedii you mind linking a tutorial? Thanks for the recommendation of affinity photo, never heard of it

[@Frontesque]

@@tstone9151 I use the whole Affinity suite for a bunch of stuff. It's not really AI driven, just a photoshop/lightroom alternative (in the case of photo)

[@Kotwurf]

Wow! This is amazing! But how to get this crazy tool? This is not Leonardo or Stable Diffusion website?

[@Geekatplay]

This is Stable Diffusion on local installation, check my channel for the videos how to install it

[@TeaBroski]

How is your computer so fast? Great stuff, thanks for sharing!

[@ferraravfx]

Amazing! I think the inpaint will solve my lipstick issues for singing videos! And I could learn more about the control nets!Thanks a lot

[@dialusdudas]

Bravo! Thanks Vladimir

[@Geekatplay]

*Thank you for your support!*

[@willjames7119]

quality walk through -- can you explain in more detail what the Lora configuration means and what it is doing? Thanks in advance

[@Geekatplay]

thank you!

[@SlimmeRevolutie]

Thank you sir for sharing your knowledge with the world! I fully watch all ads for you😂😅

[@OmekeDavidson-ut6fg]

I'm lost for words. Subscribed. This is too accurate and detailed to be free

[@Geekatplay]

thank you

[@DrSteveMorreale]

WOW! You have me very excited. I need to see where to get started with this. Looks exactly like what I want to start doing! Liked and subscribed!

[@Geekatplay]

You can do it!

[@StivenTowers]

Awesome tutorial man. Some people have recommended me stable difussion as the most accurate image2image tool, currently I'm using Midjourney and it always changes the facial features of my character. Can you tell me if stable difussion is really accurate with character consistency most of the time? Or is it as tricky as midjourney?. Thanks for your time .

[@Geekatplay]

thank you

[@Elaneor]

Thank you very much for the tutorial. Went to find those model you used.

[@Geekatplay]

thank you

[@rahul-qm9fi]

Exactly what I was looking for. Thank you.

[@Geekatplay]

thank you

[@ad2m989]

Vladimir Thank you brother, you are great And all settings are complete Best person ♥️ I hope you also look into the topic of the video freme I wanted to get a more realistic animation setting With the same settings as this video

[@Geekatplay]

I will check it out

[@ad2m989]

​@@Geekatplaythanks I really appreciate this 😘

[@EkhyOk]

It's amazing. Man, do you think that is possible apply this techinque for food photography or productos?

[@Geekatplay]

i will try that.

[@30MinsGaming]

Genius. The video and workflow technique are very much appreciated!

[@Geekatplay]

Glad it was helpful!

[@bingshenlee3477]

The video looks awesome by generating portraits. May I know program is this?

[@Geekatplay]

Stable Diffusion, local installation. kzbin.info/www/bejne/pYXVnpqOqshmm5o

[@HoangNguyen-nz4xe]

Genius. The video and workflow technique are very much appreciated! thank you

[@Geekatplay]

thank you for your support!

[@MrArrmageddon]

Does all of this still fit within 16GB VRAM or do I need more? Thanks nice video.

[@dustinjohnsenmedia1889]

I gasped out loud when I saw my original face come through the preview. Thanks for the video. It's like a real quick photoshop face swap. Do you have any suggestions on how to stylize the face a little bit? I seem to only get original face colors and details but for some images I'd like to match the generated image more and turn into an illustration.

[@Geekatplay]

thank you. you can used "styles" option. I will cover that in upcoming videos

[@draganzoddomo9890]

amazing thx, you explained it very well

[@wrylac]

Could you do this with an photo of a building or house. Keeping an acuate representation of the subject and placing it in a different environment?

[@andreleo4826]

Hey, thanks for the tutorial it helped a lot! But I have a quick question, how to make the face and the rest of the body have matching colors and tones? Which settings do I need to change? Thanks!

[@devesh2796]

Yea i was thinking the same

[@lexmitchell4402]

He didn't mention it in the video, but there is another controlNet model simply called 'color' (search for t2iadaptor color) that will make a mosiac grid like sampling of your source image colors and apply them to the generated image

[@Geekatplay]

use full body in imported image

[@erenbelvin]

@@Geekatplay could you please explain in detail? how is this done?

[@sarpsomer]

Smoooth 👍

[@Geekatplay]

Thanks 💯

[@gamersgold4984]

Thanks for this Tutorial. But I can't find the Model under the Preprocessor. I think i ticked all the right stuff in ControlNet and restarted the UI. Any suggestions?

[@Geekatplay]

you need be sure models located in correct folder, i will make video about it

[@PCtutorijali]

@@Geekatplay I dont have this model too, can you please put link for it and just write where to put model in what directory/ folder

[@SANTOSHKUMAR-zo4ef]

brilliant video !! thanks

[@Geekatplay]

thank you for your support!

[@donvittoriophoto]

I really enjoyed this video. All of your videos are great. Thanks.

[@Geekatplay]

thank you for your support!

[@domingo71]

hello Vladimir Beautiful tutorial, only I don't have the "preview annotator result" button in the control net section. Do you know how I can do it?

[@Geekatplay]

in new version it is icon, looks like spark, next to the preprocessot drop down

[@palakush7650]

Amazin amazing content,thank you

[@Geekatplay]

Glad you enjoy it!

[@stephankotter6921]

Thx so much! That's a super nice tutorial.

[@Geekatplay]

You're welcome!

[@DeGameBox_SRBT]

09:10 was it possible to use openpose_full instead of inpaint, which also captures the face?

[@Thiagomartins306]

congratulations on the job! I can use this technique to create pets?

[@Geekatplay]

thank you. i will make video specifically about pets, and yes it does works. I made a lot of photos/videos with my Border Collie

[@Thiagomartins306]

🎉🎉🎉

[@MrAlexramos8485]

great video really helped me understand how to keep the face structure, is it possible to do inpaint batch in order to create videos, that retain the face structure? working on your other video on created flicker free video and wanted to use this feature to keep the face structure consistent with my models face.

[@Geekatplay]

thank you, it is possible, but you will need to load masks for in-painting

[@Safeshelter]

Top!

[@Geekatplay]

thank you!

[@I_am_Alan]

Very nice video explainer.

[@Geekatplay]

Glad you liked it

[@charlym59]

hello Vladimir. I appreciate your videos 👍

[@Geekatplay]

thank you!!!

[@thinhnguyensb]

❤❤❤ great

[@Geekatplay]

thank you

[@blackrainboots]

Great work! Thanks so much, very comprehensive!

[@faktyimityreligijne]

Very good tutorial!

[@Geekatplay]

thank you

[@therookiesplaybook]

What video card do you have running to be able to get results that fast with all these controlnets and script running?

[@Bulldog-Chelista]

excellent, really nice

[@Geekatplay]

Thank you! Cheers!

[@matteo.g2213]

Another great video! thanks!

[@Geekatplay]

Thanks again!

[@wg218]

very cool👍

[@Geekatplay]

thank you for your support!

[@StereoVario]

Thank you, a very useful lesson. However, I ran into a problem: the preview window is not active. It exists, but it doesn't show anything. Do I need to install something?

[@Geekatplay]

on some versions (latest) preview located on side of the selection for preprocessor, it is small icon.

[@StereoVario]

@@Geekatplay Thanks!

[@ManAtPlay]

Is it should work for each checkpoint?

[@Geekatplay]

No, check points need match other components in how it was trained

[@ManAtPlay]

@@Geekatplay got it, cause I tried on what I already had and it was not working. Thnx

[@nancygtec6298]

Excellent!! Thanks!

[@antoniovoto]

thanks for the tutorial.i don't find Control sdi 15 canny.where do i can download it? thanks.

[@alessandromaia7471]

The button Preview annotator result dont show. Any tip to show this option? (Controlnet 1.1.02)

[@makulVR]

Thanks for mentioning this. Same issue for me ControlNet v1.1.112

[@Anyway-give-me-a-drink]

I have the same problem, did you solve it?

[@konigstiger93]

looks like it's set up differently now, you have to check the box that says allow preview and then click run preprocessor (the little explosion icon next to the preprocessor field)

[@Geekatplay]

it was changed, now it is small icon, on right side from drop down box. look like spark.

[@AmodeusR]

How are you using stable diffusion like that?

[@Geekatplay]

it is Automatic1111 installation (UI) and control net

[@Enchantaire]

Very interesting

[@Geekatplay]

thank you

[@aftielschwinn3535]

I noticed something about the your Stable Diffusion setup when you were using the ControlNet features There was a LORA feature just above the ControlNet menu How do I get that on my SD ?

[@ChristianBueno81]

Thanks. I was looking for a tutorial about this.

[@Geekatplay]

Glad I could help

[@ayushkastruggle3572]

I followed it entirely, I am getting my face pasted on the generation, ( I just want it to keep the structure of myface) it's not blending the face with image, how to do that, which settings to adjust, please help

[@checkmate559]

please upload same tutorial with new version lot of different getting confuse for me not showing preview option

[@SD_Alias]

Amazing! But Stable Diffusion is just too overwhelming for me. Too many options, terms, models i do not know what they do or when to use what…I envy everybody that gets into that…

[@jambrud123]

Nice nice thank you

[@Geekatplay]

Thank you too!

[@boogieman7233]

Are you using Automatic1111 gui? You're very simular to mine but I don't have controlnet.

[@Geekatplay]

you need install it in extension tab

[@amir2k469]

Thank you 😮 master , you're goat ❤

[@Cobra-gx96]

how you get that prompts ? is there any tool or site for good prompts ?

[@Geekatplay]

yes, i will release video soon about creating prompts ( prompts generators)

[@y0uKWT]

Love the video thanks, but when I use inpaint to paint the face and click generate with the same settings, it just puts the face on a random place on the image, and does not replace the face.

[@Geekatplay]

be sure you set correct masking, it may be inverted

[@WillowbarkPetPhotography]

Did you follow the prior steps to match the pose first?

[@lunathebryant]

so dope 🔥

[@Geekatplay]

thank you

[@GarethOakey]

How was this software setup? What's the install process?

[@Geekatplay]

it is Stable Diffusion, Automatic1111 installation.

[@Disly]

Спасибо, Вовчик

[@paulmp9805]

Hey man, great video but I just can't manage to get full-body persons. It's always cropped to head or upper body. Any ideas what I can do?

[@cjsim2]

This might help, I changed the first prompt to ‘full body pose’ and it gives a near on full body.

[@Geekatplay]

it was originally 2/3 photo. for full body can have tricks to add (hat) (shoes) (floor) (sky) ..etc something above object and below

[@paulmp9805]

@@Geekatplay ah nice, that sounds smart. thanks!

[@yutupedia7351]

good skills 👋

[@Geekatplay]

thank you

[@RoboMagician]

can this be achieved using leonardo or midjourney?

[@Geekatplay]

not yet

[@I_OptimusPrime]

great video. is it possible to replicate the same face from the input?

[@Geekatplay]

Yes, absolutely

[@I_OptimusPrime]

@Geekatplay I am struggling with it for several weeks now. Do we need to mask and generate again for face and features ?

[@Geekatplay]

you have option to invert mask for inpainting. you can send me email with problem. need more info on what you trying to do

[@PlayGameToday]

Hello, I ve installed Control Net, but I cant see the "Preview annotator result" buttons. Should I install another extension or what?

[@Geekatplay]

in newer version it is look like spark icon, next to the preprocessor drop down selector

[@PlayGameToday]

@@Geekatplay Ok I got it, thanks!

[@sonygodx]

Very Nice tutorial about AI workflow .

[@Geekatplay]

Glad you liked it!

[@Fiveash-Art]

How do you find out what size the model is trained on to get best results? I'm finding adjusting the size proportions of the canvas really drastically effects my image output/

[@Geekatplay]

it is in model description if you downloading from Hugingface or Civit.ai

[@Fiveash-Art]

@@Geekatplay Thanks for the reply .. Found out all the specific sizes for the model I was using. Turns out I was using an outdated version of sdxl

[@lion_king9461]

Great video👏👏👏 subsciribed👍

[@Geekatplay]

thank you

[@hmza_xd]

why i dont have upload image in controlnet img2img ?

[@trumplostlol3007]

In the future, you don't need to hire famous actors and actresses any more. Just hire someone who can act. Then transform the image of the person into someone who looks amazing.

[@Geekatplay]

possible, but you still need to base on some references

[@sirousghaffari9556]

Can this method be used for architectural rendering?

[@Geekatplay]

yes, if you using ControlNet model with architectural preprocessing. can not recall from top of my head, but i will check and post.

[@sirousghaffari9556]

@@Geekatplay If you make a post about architecture, that would be great

[@Geekatplay]

thank you for suggestion, i will

[@erwintan9848]

how to get composable lora on the bottom?

[@chenqingzhi6845]

great lesson， learned a lot ， thanks

[@Geekatplay]

thank you

[@JD-RetroRideCZ]

Hello, i have missing Preview annotator results (create blank and hide annotator also) in control net. Is there something what can i do ?

[@Geekatplay]

click on small icon next to preprocessor selection

[@PaonSol]

Well, I installed everything as well as I could, but after inputting a control net image I can't see "Preview annotator result". There's just nothing there.

[@lost-frequency]

same issue i do not have the preview result button

[@wenyuangao9198]

@@lost-frequency have you find the solution?

[@emiletetrt]

@PaonSol and @Lost Frequency Band Press the "allow preview" checkbox, then a little boom button will appear next to your choice of preprocessor

[@onejatt]

Preview button is not visible now when u try the tool see there is a icon looks like this 💥 this is the preview button just enable preview and touch this icon ur preview will be there…

[@eliasaca]

Aren't those controlnet modules unsafe due to pickle imports being detected?

[@Geekatplay]

they are using some calls, that may misused, it is why i usably check phyton code it self, if code not in the safeguard settings

[@lyesakkouche8285]

Hi, it looks like , version of Imac is differente of windows ! how to install it in windows ?

[@djivanoff13]

Composable Lora-I have a completely different menu(where can I download your version?

[@Geekatplay]

github search for Automatic1111

[@djivanoff13]

@@Geekatplay I installed it, but I have a different menu than you have in the video

[@djivanoff13]

@@Geekatplay Composable Lora ▼ Enabled Use Lora in uc text model encoder Use Lora in uc diffusion model

[@cjsim2]

I am following along with mac, I have the v1-5 , looking in settings has all settings except ControlNet, any ideas?

[@Maltebyte2]

I just cant get anywhere i have image A and when i generate someting in image to image i get a cow! for example!

[@EZZYLAND]

how can we batch inpaint? for the purpose of processing png sequences

[@Geekatplay]

you can create multiple masks and load them as batch

[@ifoundthistoday]

thank you !!

[@Geekatplay]

any tiime

[@Sagadyn]

Thank You

[@Geekatplay]

You're welcome

[@iamjustanowl4109]

name of the tool kit pls

[@moonduckmaximus6404]

where do you get the checkpoint and how do i install please?

[@Geekatplay]

you can copy checkpoint to the model folder

[@worldofgames2000]

Very good tutorial! Thank you!

[@Geekatplay]

You are welcome!

[@AaliDGr8]

@@Geekatplay is it automatic 1111 or something other?!