Use Any Face EASY in Stable Diffusion. Ipadapter Tutorial.

  Рет қаралды 165,744

Sebastian Kamph

Sebastian Kamph

Күн бұрын

Пікірлер: 262
@sebastiankamph
@sebastiankamph 10 ай бұрын
Text & image guide for Patreon supporters www.patreon.com/posts/use-same-face-ip-98117124
@LouisGedo
@LouisGedo 10 ай бұрын
👋
@brianckelley
@brianckelley 10 ай бұрын
Dude. Why have you burned subtitles into this video!? You probably have no idea how distracting it is for people with ADHD. There's a big button to enable closed caption inside a YT video (which YT generates automatically) on every single platform and its turned off by default for a reason. I can't get anything from this tutorial with those subs burned in. Love the content, Sebastian. Been watching for a long time. But this one, and any others with burned subs, is a no go for me and possibly others. Shame. I couldn't wait to dig in to this one.
@kayinsho
@kayinsho 10 ай бұрын
Great vid. Can you use the new Stable diffusion Web UI Forge with this? Automatic 1111 is a mess.
@KDawg5000
@KDawg5000 10 ай бұрын
One thing nice about using Ip-adapter first, to create the base image, is that it creates a good image to use Reactor for a face swap. So if you want an image that very closely resembles yourself, just use Reactor to swap your face back on there. :)
@sebastiankamph
@sebastiankamph 10 ай бұрын
That's actually... pretty clever 😅🌟
@ADZIOO
@ADZIOO 10 ай бұрын
This is an option, but so what if using this adapter with Lora significantly spoils the render quality? It's probably not worth it.
@Al-Storm
@Al-Storm 9 ай бұрын
Great tip. I'm getting better results with reactor than using controlnet.
@albyok27
@albyok27 3 ай бұрын
Yes, but only if you're aiming to generate a realistic image. Reactor is not good when you wanna make a very deformed version of someone.
@avmsteve
@avmsteve 10 ай бұрын
I had been aware of this extension for a few days, but after looking at some other guides (and being confused) I decided to wait for yours, which as anticipated was clear, concise and comprehensive. Thanks Sebastian.
@sebastiankamph
@sebastiankamph 10 ай бұрын
Happy to hear that! :)
@TeosAntagonian
@TeosAntagonian 10 ай бұрын
Hello Sebastian. Thank you very much for your insightfull tutorials. I started playing with SD thanks to you. I just recently installed forge as instructed in your video but how do I install IP adapter plus on forge? I did the same as in this tutorial but I dont get the proper selection for the preprocessor. I can select ip adapter plus for the model but not for the preprocessor.
@raphalopes495
@raphalopes495 10 ай бұрын
I'm facing the same problem. Did you find a solution?
@CHASMITHADHARAVATH-sb8sw
@CHASMITHADHARAVATH-sb8sw 10 ай бұрын
same here @@raphalopes495
@SebyRockCostantino
@SebyRockCostantino 9 ай бұрын
Same problem here@@raphalopes495
@Al-Storm
@Al-Storm 9 ай бұрын
Any luck?
@scarekrow1264
@scarekrow1264 9 ай бұрын
+sebastiankamph Questionmark.
@sn0wbr33z3
@sn0wbr33z3 10 ай бұрын
Good thing this is available for SD 1.5. Not everyone is able to catch up with SDXL.
@MrCRFultz
@MrCRFultz 10 ай бұрын
set it up exactly as he did, not even close to looking like my input images, seems to be alot of how to videos on sd, not any of them will give the same results as posted. moving on to the next one.
@DeVirginer
@DeVirginer 6 ай бұрын
Same here.
@donschannel9310
@donschannel9310 10 ай бұрын
its not working when i use my model face in multiple or even in single
@osrsdreambot4006
@osrsdreambot4006 10 ай бұрын
Same here this method doesn't work with multiple images
@joechip4822
@joechip4822 2 ай бұрын
Unfortunately everybody who shows face swaps only shows them with portrait images as the target. It would be much more interesting to know whether this also works sufficiently with scenes where the environment is more important, and the person is shown with a full body, meaning the target face is significantly smaller ... !?
@frankiesomeone
@frankiesomeone 8 ай бұрын
Can ForgeUI do multi-input? I'm trying to use batch folder and batch upload but I think they only use the first image.
@RikkTheGaijin
@RikkTheGaijin 10 ай бұрын
Among all the other similar face-transfer systems (Roop, ReActor, InstantID) this one seems to give me by far the worst results. The likeness is really bad and the overall image quality is terrible.
@lucianodaluz5414
@lucianodaluz5414 10 ай бұрын
Did you try Faceswap lab? It is the best I've seen so far.
@TRoJMelencio
@TRoJMelencio 10 ай бұрын
is there instant_ID for 1.5 yet?
@lucianodaluz5414
@lucianodaluz5414 10 ай бұрын
No@@TRoJMelencio
@ADZIOO
@ADZIOO 10 ай бұрын
There is no reason to use this it gives tragic results, I try all the time to get some good effect with SDXL and the same poor results, all the time quality problems.
@lucianodaluz5414
@lucianodaluz5414 10 ай бұрын
@@TRoJMelencio no
@madwurmz
@madwurmz 4 ай бұрын
nice! to the people saying it doesnt work , check if there is the error "("Insightface: No face found in image.")" then increase the padding around faces in the images to help the face detection model, also just to be sure make the controlnet images bigger than 512px 🤗
@danieldimitrovdrums
@danieldimitrovdrums 7 ай бұрын
Great tutorial. Works really well with SD1.5, but with SDXL - bodies and faces seem way off and very unrealistic (despite negatives), unless it's close-up portrait facing the camera. Instant-ID gives me similar results with SDXL, not great for anything but portraits.
@influencericons9373
@influencericons9373 5 ай бұрын
Hey this is a great video, thanks for sharing. Can you advised on how to make the backgrounds clear and not blurry as every image generated leaves the background out of focus.
@CapsandCaravans
@CapsandCaravans 9 ай бұрын
I have forge UI and i dont know how to get this working. preprocessors for for Face Id dont appear
@zoro_uchiha777
@zoro_uchiha777 8 ай бұрын
did you find any solution?
@waurbenyeger
@waurbenyeger 10 ай бұрын
I'm using forge and I don't have the face id plus preprocessor ... where can I find that and where do I put it?
@zoro_uchiha777
@zoro_uchiha777 8 ай бұрын
did you find the solution
@waurbenyeger
@waurbenyeger 8 ай бұрын
@@zoro_uchiha777 With Forge the default IP-Adapter preprocessor called "InsightFace+CLIP-H (IPAdapter)" works just fine. Just follow what he does with everything else and it will work. Also, you might not need to use the LoRA, but if you do I find that switching the number at the end from 1 to 0.4 gives better results.
@forestlong1
@forestlong1 10 ай бұрын
Very strange work of the controlnet, the IP adapter V2 worked a couple of times and then began to produce completely worthless results completely different from the sample photos that I uploaded.
@Oryon520
@Oryon520 10 ай бұрын
Best settings: LORA: 0.65 Guidance controlnetNet: 1.25 Keep Start 0 and end 1.0
@sebastiankamph
@sebastiankamph 10 ай бұрын
Interesting, thanks!
@10mmlover
@10mmlover 10 ай бұрын
You're definitely on to something concerning lowering the weight of the lora. The higher the weight, the more it wants to zoom whatever picture you're generating into a portrait. If you lower the weight, it zooms out so there's more going on. (aka me riding a unicorn and wielding a sword riding into battle)
@tag_of_frank
@tag_of_frank 9 ай бұрын
Seems like a good way to test your input images before making a textual-inversion or lora.
@ziffano8940
@ziffano8940 10 ай бұрын
Great tutorial, 100% spot on. I'm new to SD. Is there a way to save the "outcome" of the face, so you can use it later?
@rwarren58
@rwarren58 8 ай бұрын
We need an answer, good sir.
@Yoshi92
@Yoshi92 6 ай бұрын
8:29 The edit with the music is just too funny man I actually had to laugh 😂 Thank you for the tutorial! :)
@BayuRahmawan_id
@BayuRahmawan_id 5 ай бұрын
Got error unable to import dependency ,how ?
@CoconutPete
@CoconutPete 10 ай бұрын
wonder if this would work with SSD-1B?
@Schopenhauer404
@Schopenhauer404 28 күн бұрын
You explain it perfectly!
@shenlOng8664
@shenlOng8664 2 ай бұрын
how to fix preprocessor not showing ip adaptor clip sd15 or any other models related to faceid....?
@Sviddenofficial
@Sviddenofficial 9 ай бұрын
Hey! Thanks for this great guide! Unfortunately it doesn't work for me, just results in images of random people.
@lanoi3d
@lanoi3d 8 ай бұрын
Did you find a solution? I get the same. I also tried using with and without ipadapter and the results are the same. I think maybe this has recently broken? I only recently downloaded all the latest versions of everything but this ipadapter face thing doesn't seem to work.
@popcornviews
@popcornviews 5 ай бұрын
same here, would love to hear if anyone found a solution to this
@VirgilLucaRusan
@VirgilLucaRusan 9 ай бұрын
Man, controlnet is not working at all for me. I have installed the extensions and all of its models and uploaded them and everything but stablefusion is completely ignoring it. Yes I pressed enable and did everything from the videos. Please any advice or a discord server or anyone to whom I can share screen so he can maybe see where the problem is?
@devillmay
@devillmay 8 ай бұрын
I had the same case. But I resolved it after changing/playing with the parameters. The given parameters for ip-adapter-faceid- plusv2-sdxl parameters didn't work with me. And I went for ip-adapter-faceid- plusv2-sd15 paramaters. It didn't work with the parameters Sebastian gave in the video. It started working after I changed the CFG from 1.5 to 5 and the Sampling to 20. And only then my SD started recognizing Controlnet. I was able revert it to what Sebastian suggested in the video once it started working. My best results came with: ip-adapter-faceid- plusv2-sd15 - Sampling 30 - CFG 8 - Control Weight 1.0
@RZ370z
@RZ370z 10 ай бұрын
for some reason I am having difficulty adding the upgraded version of controlnet to ForgeUI, anyone else having this issue? - may be conflicting due to already build in controlnet?
@levis89
@levis89 10 ай бұрын
Do we need any trigger word in the prompt for the lora we have added
@sebastiankamph
@sebastiankamph 10 ай бұрын
No, it's weighted in when you add it like I did.
@levis89
@levis89 10 ай бұрын
@@sebastiankamph gotcha, thanks for replying!
@DaKussh
@DaKussh 8 ай бұрын
any tips for choosing the most adequate samples images? resolution? background? portrait angles? number of samples?
@blademarketing
@blademarketing 10 ай бұрын
Drives me crazy, I am trying and i keep getting an error Exception: Insightface: No face found in image. its like control net doesnt really do anything and i made sure its enabled, uploaded 6 photos 1000x1000 very clear face in them... any ideas?
10 ай бұрын
The subtitles are really helpful!
@sebastiankamph
@sebastiankamph 10 ай бұрын
Thank you for the feedback! Happy to hear it
@simile20
@simile20 10 ай бұрын
Nice tutorial Sebastian. But why it doesn't work with batch images? Only with single image input.
@dreamersrealm6389
@dreamersrealm6389 7 ай бұрын
Is there a specific version of dream booth everyone uses? Mine looks very different compared to some.
@gentopics360
@gentopics360 8 ай бұрын
thanks for your tutorial! but what can I do wehen I see this: AttributeError: 'NoneType' object has no attribute 'mode'?
@jombbobbo6291
@jombbobbo6291 9 ай бұрын
How does this compare to reactor? that's the best one i've found, but of course always looking for something that might be better
@Aidenkeagan
@Aidenkeagan 10 ай бұрын
Is there a way we can generate images with the same face and clothing but in different pose?
@mbfcs2
@mbfcs2 9 ай бұрын
Woh ! Thanks for this very useful video, such a good job ! I'm a newbie and your videos are perfect to me. I've tried and it's amazing, even though for now all the characters in the image looks the same 😂
@AITullball3333
@AITullball3333 10 ай бұрын
The faceid portrait model is even better.
@sebastiankamph
@sebastiankamph 10 ай бұрын
Hey! I'd love to know in what ways you find it better. Been playing with the latest 1.1 and not really seeing much (and limited to 1.5)
@AITullball3333
@AITullball3333 10 ай бұрын
@@sebastiankamph I get much better likeness, and it's super good for mixing faces. Realisticvision5, ddpm, 50-60 steps, 4-5 cfg, weight at 1.0, 0-1.0. I think that the input images are very important. I use five, and they're all 768x768 taken from almost the same angle and distance, with a little bit of distance around the head. Using comfy. I guess this all might depend on the subject. I haven't tried it with many different faces. I never had much luck with sdxl anyway :\
@lucianodaluz5414
@lucianodaluz5414 10 ай бұрын
Is this a Controle Net thing? Can you share the link?
@AITullball3333
@AITullball3333 10 ай бұрын
@@lucianodaluz5414 Or just look at Sebastian's link in the description.
@benharris144
@benharris144 10 ай бұрын
May I ask what you mean by this?
@rd-cv4vm
@rd-cv4vm 8 ай бұрын
Hello, thank you for the tutorial, i am using forge, i am unable to find the proper pre processor in my list or online, i have InsightFace+CLIP-H (IPAdapter) only. it isnt the same as you
@MauricetePas
@MauricetePas 8 ай бұрын
Don't forget to enable your Controlnet module which very subtlety happens here. 4:34 And I was just wondering why my images didn't look anything like me. 😂 Other than that, great tutorial !! Thanks! 👍
@sebastiankamph
@sebastiankamph 7 ай бұрын
Glad you found it! :D
@pranaydas3320
@pranaydas3320 3 ай бұрын
Thanks! I was wondering why my images didn't look the same😂
@Ork-Schamane
@Ork-Schamane 6 ай бұрын
How i can get the "DPM++ 2M Karras" Sampler (or other Sampler)? I can't select it on my newly installed Stable diffusion 1.5
@azucii
@azucii Ай бұрын
since it works with SDXL will it works with ponyXL model? or IllustriousXL model?
@jelacerda5960
@jelacerda5960 7 ай бұрын
how do i can change the ControlNet Integrade for this ControlNetv1.1.440?
@kakaoxi
@kakaoxi 5 ай бұрын
When i use it on stable xl it says to me a strange error, also if i put sd xl vae and all to xl
@Harley_the_Sosig
@Harley_the_Sosig 7 ай бұрын
Has this been disabled? I had this working down to perfection for my face but took 4 weeks away and now it doesn't work, it just renders random guys faces even when I use all my same pics
@popcornviews
@popcornviews 5 ай бұрын
did you find a solution? I also get just random faces, not the face of the images I upload
@Harley_the_Sosig
@Harley_the_Sosig 5 ай бұрын
@@popcornviews i have but its hit and miss, it works better with between 2 and 4 images of the face. Also found out I had some more updates to do
@AboutDaWorld
@AboutDaWorld Ай бұрын
Can you do this on COMFY UI?
@eugenekhristo7252
@eugenekhristo7252 8 ай бұрын
Why Starting Control Step and Ending Control Step sometimes doesn't affect output render at all. And if I set 0.2 - 0.8 as in your example, I have zero resemblance on ref images 😂😂😂 And should I change extension of .bin to .pth? Or atm it doesn't matter? Thanks
@Warrioroffaith11
@Warrioroffaith11 7 ай бұрын
How do you create a consistent body? cause I know how to do the face swap but I can't seem to get a consistent body though.
@Sing00525
@Sing00525 8 ай бұрын
Hello Sebastian. Thank you for sharing. I tried with Reactor and the ipadapter on SD1.5 txt2img under the same prompt (with lora when using Controlnet). When I use the ipadapter, the photo becomes so blurred like a glare covered. What parameters should I adjust?
@iceman1125
@iceman1125 8 ай бұрын
did you get resembling faces? I am trying to use his methods to resemble the face however they are not at all close and seem generic
@toon4367
@toon4367 10 ай бұрын
Great turtorial! but i have one problem. My stable diffusion generates 2 or more people 50% of the time. Is this a common problem?
@ArtesGraficasDigitales
@ArtesGraficasDigitales 7 ай бұрын
¿Cómo llegamos a la página que muestras cuando empiezas el video?
@LeshaKhaletskiy
@LeshaKhaletskiy 6 ай бұрын
if my root controlnet folder is "models/Controlnet preprocessor" and "models/Controlnet" what folder im need to use for import preprocessor? im put safetensor file in both of them and models/lora but custom preprocessor don't adding, custom models adding well
@bassieboot2120
@bassieboot2120 10 ай бұрын
im trying to use it with force but it wont see the bin files
@jeffreypodcasttv
@jeffreypodcasttv 8 ай бұрын
someone help me with this solution please, when I choose the multiple option this is what appears '' loadsave.cpp:1121: error: (-215:Assertion failed) !image.empty() in function 'cv::imencode' '''
@daxtv6168
@daxtv6168 7 ай бұрын
do you have the link for the said app?
@yosribengaidhassine9299
@yosribengaidhassine9299 7 ай бұрын
which is better ReActor or IPadapter
@jonathanedward5288
@jonathanedward5288 10 ай бұрын
How do you use ipadapter with FORGE? I tried on FORGE but the result not as good as original auto1111
@GodLikesMoe
@GodLikesMoe 10 ай бұрын
Are there any requirements for the quality or type of image used as an input? Also, is the amount of input images important? I can't get any good results. At times, you can't even recognize anything at all.
@filmyentity
@filmyentity 10 ай бұрын
I Followed the same steps but its not working as shown in the video the resemblence is not at all matching
@ameet21
@ameet21 9 ай бұрын
you please show us how to merge sdxl train model with other sdxl model... like we do with sd 1.5 checkpoint merger where in A we use to put our train model on B we use to put Photon or dreamshaper and on C pruned checkpoint, and as VAE 56000 or 84000 so we want to see tutorial on SDXL
@Sysshad
@Sysshad 9 ай бұрын
Better than reactor? becausee that one is really good. And also much easier to setup
@raphalopes495
@raphalopes495 10 ай бұрын
First, thanks for the video, your channel is really helpful in keeping up to date with all changes, and you explain everything very well. I've been using Reactor for a few months to generate a consistent face for a model, and I really like it. Decided to give this a try, and I was expecting to get similar results with this method (but somehow better and/or more consistent), however that's not what happened. The face swaps I'm getting with IpAdapter are very different from the results I get with Reactor, it seems like another person, which makes this method not very useful for me (at least for this particular project, which already has a strongly defined face). Is this normal? Any tips to improve? For now I will keep using Reactor, since it's giving me better results.
@musicandhappinessbyjo795
@musicandhappinessbyjo795 10 ай бұрын
Was this video re uploaded. But anyway. Could you do a video with comfy UI using this workflow?
@sebastiankamph
@sebastiankamph 10 ай бұрын
Yes, was an error, had to reupload :)
@mihalisization
@mihalisization 10 ай бұрын
What's the difference between this method and the old one where we use the ReActor extension? Are there any benefits to using IPAdapter?
@sebastiankamph
@sebastiankamph 10 ай бұрын
Reactor with its insightface model is best at photorealism, whereas ipadapter can do any style.
@mihalisization
@mihalisization 10 ай бұрын
thnx @@sebastiankamph you are right!
@forestlong1
@forestlong1 10 ай бұрын
How does this work in ImageToImage or Inpaint ?
@Beltramstein
@Beltramstein 9 ай бұрын
I think the pre-processors name changed to InsightFace and CLIP ViT on newest Forge.
@vurmamivurdu
@vurmamivurdu 7 ай бұрын
Can this somehow work with Fooocus?
@Elwaves2925
@Elwaves2925 10 ай бұрын
If I met you in a dark alley at night it would be a pun-ishing time for both. 🙂 I stumbled onto this through trial and error but was missing the settings to get good results. Cheers.
@Airbag888
@Airbag888 9 ай бұрын
I'm guessing this is not going to help for groups? I'm trying to recreate family pictures of us on the moon and more haha, does this work with the fork that uses directml for AMD GPUs? it does not seem to be taking my pictures in consideration
@silentwindstudio
@silentwindstudio 9 ай бұрын
What is the full name of the extension? Typing ControlNet gives me a billion results.
@Nutronic
@Nutronic 10 ай бұрын
Where's your baseball cap from? I need a new one 😊
@jump-do
@jump-do Ай бұрын
Not working - error AttributeError: 'NoneType' object has no attribute 'mode'
@Chuckq1
@Chuckq1 10 ай бұрын
AttributeError: module 'torch.nn.functional' has no attribute 'scaled_dot_product_attention' all i get
@josephwestphal292
@josephwestphal292 10 ай бұрын
I use A1111 and in the controlnet it does not show me the Models beside the preprocessor. what could i have done wrong? Controlnet is 1.1.440, i restated all multiple times ... i put the folder into stablediffusion > models > stable-diffusion and extracted them
@sebastiankamph
@sebastiankamph 10 ай бұрын
For a1111, the controlnet models folder is stable-diffusion-webui\extensions\sd-webui-controlnet\models
@josephwestphal292
@josephwestphal292 10 ай бұрын
Thx a lot! I will try again@@sebastiankamph
@anotherdimension2915
@anotherdimension2915 8 ай бұрын
Why is my local Automatic1111 setup missing DPM++ 2M SDE Karras sampling method? I only have DpM++ 2M, first time fresh install this April 2024, someone please any ideas...
@devillmay
@devillmay 8 ай бұрын
I have the same issue. Any idea @sebastiankamph ?
@Necksteppa77
@Necksteppa77 9 ай бұрын
Hey, IDK what im doing wrong. I followed step by step, by my images turn into messy kaleidoscopes as soon as I enable controlnet. Any ideas what im doing wrong?
@Freelaughter420
@Freelaughter420 8 ай бұрын
What happens when you turn preprocessor to 1024 instead of 512 when using sdxl checkpoint ?
@sebastiankamph
@sebastiankamph 8 ай бұрын
Just use pixel perfect instead
@benharris144
@benharris144 10 ай бұрын
It's great when it works, but for some reason it just stops working randomly. I don't know what causes this.
@dqschannel
@dqschannel 8 ай бұрын
Do you know if this works with Fooocus?
@MisterWealth
@MisterWealth 10 ай бұрын
My images turn out to be an absolute mess, it isn't working at all. Anyone know why? I have the same exact version of controlnet, same models, same res, same sampling method with steps and resolution. Same model, but the faces are just glitchy
@qbcle
@qbcle 10 ай бұрын
I laughed for 3 minutes 🤣🤣🤣 nice tutorial btw
@mada_faka
@mada_faka 10 ай бұрын
Hi sir, thank you so much for video, you always bring best tutorial stable diffusion.
@sebastiankamph
@sebastiankamph 10 ай бұрын
So nice of you, thank you :)
@Umermehmood-jo6gv
@Umermehmood-jo6gv 10 ай бұрын
how you get all foocus styles in A 1111.
@filterophilicxx5914
@filterophilicxx5914 10 ай бұрын
why it processed only one picture i added multiple pictures "ControlNet - WARNING - Insightface: More than one face is detected in the image. Only the first one will be used."
@artist.zahmed
@artist.zahmed 10 ай бұрын
can help me about sdxl training model i have a good pc with rtx 4090 but i dont know how to train xl model for my personal data
@Lw24_AI
@Lw24_AI 8 ай бұрын
How much video memory do you need on these controlNet models. I have 12gb of video memory and still can't handle it
@sebastiankamph
@sebastiankamph 8 ай бұрын
12gb should be fine. Have you tried lowering your resolution?
@Lw24_AI
@Lw24_AI 8 ай бұрын
@@sebastiankamph 512х720 It is on the 1.5 models on SDXL there is no memory at all on the juggernaut model.
@gamingoutloud293
@gamingoutloud293 10 ай бұрын
thanks for the video, i find it quite hard to get into SD. There are so many options, i have the feeling its overcomplicated. We need more simple ui.
@mangashba
@mangashba 10 ай бұрын
does this work in Forge ? The preprocessor doesn't seem to appear there
@DannySmith-bg1pk
@DannySmith-bg1pk 8 ай бұрын
I have the same issue. Were you able to find a fix for this?
@mangashba
@mangashba 8 ай бұрын
@@DannySmith-bg1pk nope, I gave up on it
@RedBalloonArtWorks
@RedBalloonArtWorks 9 ай бұрын
When I follow the steps, it starts doenloading 2.35gb file first on the following path stable-diffusion-webui\extensions\sd-webui-controlnet\annotator\doenloads\clip_vision\clip_h.pth
@RedBalloonArtWorks
@RedBalloonArtWorks 9 ай бұрын
Is it one time thing?
@sebastiankamph
@sebastiankamph 9 ай бұрын
Yeah, one time requirements
@botlifegamer7026
@botlifegamer7026 10 ай бұрын
So what is the best lora?
@holly11111111
@holly11111111 9 ай бұрын
made all the steps but still cant get the same face that I need, i even also put higher the Control Weight :( heeeeelp
@IngridUterus
@IngridUterus 7 ай бұрын
But how to keep unique special elements like birth marks etc?
@sebastiankamph
@sebastiankamph 7 ай бұрын
Tough one. I would probably retouch them in manually unless you want to specifically train a model.
@NRubric
@NRubric 10 ай бұрын
For me ControlNet "Preprocessor" didn't show "ip-adapter_face_id_plus" or anything with ip-adapter. I only get "InsightFace+CLIP-H (IPAdapter)", "CLIP-ViT-bigG (IPAdapter)" and "CLIP-ViT-H (IPAdapter)".
@Oryon520
@Oryon520 10 ай бұрын
U use Forge ?
@accountgoogle-b9d
@accountgoogle-b9d 7 ай бұрын
@@Oryon520 for me too, and i use forge
@0oORealOo0
@0oORealOo0 9 ай бұрын
it's not better ReActor?
@eduardmart1237
@eduardmart1237 3 ай бұрын
Did you trained your own model?
@darkazurr9891
@darkazurr9891 8 ай бұрын
i got it all installed im just trying to get it to look like my photo but it comes out nothing like them XD so i gotta play around see what i did wrong , great guide tho it looks great even tho its not me XD
@popcornviews
@popcornviews 5 ай бұрын
did you find the solution?
@cai567890
@cai567890 10 ай бұрын
Can used it at Intel graphics?
@miraoasisgaming2495
@miraoasisgaming2495 6 ай бұрын
I think I watch your videos more for the dad jokes so I can annoy my kids more effectively LOL
@BMagor57
@BMagor57 7 ай бұрын
How come if I'm doing what he is doing my pictures end up looking nothing like the person...
@TomiTom1234
@TomiTom1234 10 ай бұрын
Great tutorial as always. I laughed at 8:46 😂😂
Inpainting in Stable diffusion for beginners.
6:52
Sebastian Kamph
Рет қаралды 143 М.
WOW! NEW ControlNet feature DESTROYS competition!
9:08
Sebastian Kamph
Рет қаралды 382 М.
Леон киллер и Оля Полякова 😹
00:42
Канал Смеха
Рет қаралды 4,7 МЛН
1% vs 100% #beatbox #tiktok
01:10
BeatboxJCOP
Рет қаралды 67 МЛН
ULTIMATE FREE LORA Training In Stable Diffusion! Less Than 7GB VRAM!
21:14
How to change clothes with AI.
14:45
Sebastian Kamph
Рет қаралды 116 М.
Stable Diffusion ControlNet tutorial by Sebastian Kamph
10:06
ThinkDiffusion
Рет қаралды 3,2 М.
How to use Stable Diffusion. Automatic1111 Tutorial
27:10
Sebastian Kamph
Рет қаралды 352 М.
Ultimate Guide to IPAdapter on comfyUI
30:53
Endangered AI
Рет қаралды 32 М.
How to AI Upscale with ControlNet Tiles - High Resolution for Everyone!
18:16
Леон киллер и Оля Полякова 😹
00:42
Канал Смеха
Рет қаралды 4,7 МЛН