Could you make a tutorial creating a custom mask in a photo editing App like Gimp or Photoshop and show how to use in IMG2IMG/Inpainting? I would really appreciate it.. I've searched high-n-low for a detailed tutorial, to NO avail.!!! I'm sure others may find it helpful. Thanx :)
This was a great tutorial! One point though: when using latent noise as the infill option, you don't retain anything from the original image, it gets overwritten by pure noise. That's why a low denoising strength didn't work. It makes sense to always use a denoising strength of 1 when starting from pure noise. Outside of inpainting, when you're generating a new image, it does start from pure noise and denoises it to a final image, so you're just repeating the same process in a smaller area.
Good tutorial for changing clothes, close to how I do it! I would recommend using controlnet openpose as well, especially on high denoise inpainting might start to introduce slight differences in the subject's body and pose, so having openpose on the original image keeping the subject in place will save a lot of headache.
Thanks! Yeah, I sometimes dig up ControlNet for it, but I find it's mostly for my extreme cases, and not for people learning to use inpainting. Good tip, thank you!
ComfyUI made sense when the workflows were simpler than A1111. Now it's just ridiculous amounts of nodes that take way more effort to set up than using A1111 hence why they're creating websites where people can download the workflows that are then quite messy to tweak or modify, which is basically absurd.
Another fantastic guide. Great tip with the "s" shortcut for a larger painting area! I used to use Shift+scroll-wheel, but it gets a bit finicky sometimes.
Thanks for the video! Inpaint sketch is a really nice tool to use for something like this as well :) I usually paint the area with the colour I want to use and general shape (as in for example adding a heart necklace), then do Inpaint on the same area to "refine" it :)
Instead of generating different pants based on prompt, is it possible to upload a picture of the pant of your choice and ask the model to generate a picture based on the pant picture you uploaded?
Obviously there are far better and easier ways to do inpainting (and it's been used for a long time to change far more than just clothes), but this is great for someone just starting out!
Is there an option to combine outfits from one image and the rest (model, face, pose, hands) from another? I recall an option with controlnet, not sure about the correct terms. Perhaps scene decomposition? It automatically added tags to certain parts of a scene, like painting or window. Does this exist for people? It would be nice to create different assets, like faces, hands, hairdos, clothes and rigged human models (perhaps as a set of images from different angles). If you have these, what is the best way to combine these in a consistent way?
Great video, thank you. Sebastian, do you have solution for this problem: when you use Reactor for face-swaps, it works great with photograph style images, but if you try it with a painting-style the swapped face will look too photo-like and does not blend well with rest of the image. Any tips how to adjust it?
Is it possible to change an uploaded image’s style completely with a model from Civitai? For example if the model is to change something into a film noir style etc but without deviating from the original image too much
Use img2img and control net for this. Put your source image in the control net (use open pose/depth/canny models depending on needs) and put your style ref in the img2img input. The style ref doesn't even have to look anything like the model image, it's just for the look. This workflow will force stable diffusion to keep the structure of your model image but try change it to match the style of the reference image with the aid of your prompt. Then play with the denoise strength till you get what you want.
@@Kal-el23 haha, hardly a pro, but I know the workflow works. @sebastiankamph actually has a video on exactly this, so he will prob explain it better. The thumbnail is of a lady in the same pose in 3 different styles I think? But another great tool for doing this in a quick and easy way is to use something like "krea" and load an image into the canvas...then just type the new style into the prompt. There are other online platforms that also do these kind of style transfers. Not as customisable and in depth as stable diffusion but sometimes you don't need that level of control, and the tweaking can take a long time. Krea is a real time diffusion engine so the changes you make you can see affect the result as you go, making iterations muuuuch quicker.
Do you happen to know what use cases will allow inpainting models to work? Because most of the time I find inpainting models to be worse than the original model for inpainting so I just deleted them.
Hi. Could you assist me how to preserve the details of graphics on T-shirt? For example, I tried a tshirt with Jurassic park as text with graphic jurassic logo but the result is weird as unreadable text and graphic. How to get to some near to the generation? Thankyou
you must be skipping a crucial step. I have a t-shirt that I'm trying to change into a sweater. I follow your steps and it remains a t-shirt. My prompts are sleeveless sweater. Shouldn't that work?
How can AI be leveraged to create a background for a furniture image in a seamless and aesthetically pleasing manner, considering factors such as lighting, perspective, and style compatibility?
Hi, i am new to this. Is there a tutorial of how to setup stable diffusion. I went to stability ai but i cannot see there how to get to the screen your are showing above. Apreciate any help
You can run it locally on your PC, but you will need about 8GB VRAM minimum. This version is called Automatic1111 and is easy to install. Many guides online
Nice examples but some of them don’t look too realistic. Idk if that is because of the selected model or what. Do you have any suggestions for getting more realistic results ? What’s the difference with keeping on original vs latent noise?
Thanks for the guidance, however we been wondering you should make a video on how to keep the same clothes consistent, that would more useful because AI keeps changing the clothes layout.
How about if we want to change to a specific power of outfit from another source ? Does IP adapter work or need to train a new LoRa on the outfit and apply to replace ?
Hi, I have a question for you that might be a good idea for your next content. I'm new to using Automatic1111 and the file size is getting bigger, around 40GB. I'm using ControlNet and have downloaded the extension or model seg, depth, etc. for ControlNet. When I use depth and see the preview of the depth image, will it download again in the CMD section? I thought that once I had downloaded parts of ControlNet like depth, seg, etc., it wouldn't download again, but it turns out it still downloads other parts in CMD. This also applies to extensions. Is that how it works? Or will it only download the remaining parts in CMD when using depth, etc. for the first time?
Wouldn't it be more suitable to use the sketch mode in general if one wants clothes in different colors. So in this case not only for the hat but for top and bottom clothes too?
Why are clocks different from AI images? They have the right amount of hands. While I knew this it reminded me that I really need to use inpainting more to fix and add to images. Cheers.
I was thinking: Is it possible I take a picture of my friends clothes and using stable diffusion move these clothes to my picture? like I dressed with these clothes without distort or change any part of clothes?
I'm not 100% certain but I don't think so....not the way you describe. You could load the image of yourself, mask an area and then describe your friends clothes. That would work to some degree, depending on what your friend is wearing.
That’s cool, although I’m looking how to apply consistent clothing to my character. So, if I’m going to give them a white crop top, then I want it to be a crop top of a specific style with a specific design to it. If I’m going to give them a red hat, I want it to be a red hat that looks a specific way. Most of the time, when I change my character’s clothes, I want it to be clothes within their wardrobe, rather than random clothes. I wonder if there’s currently any way to maintain consistency in clothing.
@@transporter3231 Yes, but not easy. Most don't support amd natively. Linux can manage it easier I believe. If you don't want to go through the amd mess of stable diffusion, I would just get a nvidia or use cloud solutions.
I have also noticed that using "whole picture" changes how the AI responds to prompts. It actually seems to consider the entire image as part of what it's trying to generate if you go with "whole picture," while it will ignore the unmasked portion in considering what it's trying to generate if you do "masked only." For example, if you want to give Doctor Strange a third eye in his forehead, some models will utterly refuse to put three eyes onto a person; it will keep just making weird smudges where you inpainted for that eye. But if you do "masked only," it will ignore that there are eyes on the face already, and generate an eye where you put the mask. So, if you have a stubborn model and don't know a better one to use for what you're trying to do, "masked only" can help you force changes. On the other hand, if you want to ensure that whatever you're doing fits in with the rest of the image, by being considered as part of the whole, "whole picture" helps a lot with that.
same issue here! Sometimes miniature humans at the size of the mask (for instance, a person wearing pants, or vanished pants). Also, in my case, other times it generates incomplete objects or vanished ones. I woukd like to know why because inpainting on Foocus and ComfyUI works great and quick, but man I want to like A1111 and try to understand why generates garbage results.
Your denoise value is too high, so the original content is not being respected. For original text2img we usually use about 0.75, but for inpainting small areas, you can use much lower (maybe 0.30). OR, and this is better: use pose controlnet-- then you can use higher denoise without losing the original composition.
*/• I believe we are meant to be like Jesus in our hearts and not in our flesh. But be careful of AI, for it knows only things of the flesh such as our fleshly desires (without fear of God) and cannot comprehend things of the Spirit such as true love and eternal joy that comes from obeying God's Word [Galatians 5:16-26]. Man is a spirit and has a soul but lives in a body which is flesh. When you go to bed it is the flesh that sleeps, but your spirit never sleeps and that is why you have dreams, unless you have died in peace physically. More so, true love that endures and last is a thing of the heart. When I say 'heart', I mean 'spirit'. But fake love, pretentious love, love with expectations, love for classic reasons, love for material reasons (love because of material needs) and love for selfish reasons outside God those are things of the flesh. In the beginning God said let us make man in our own image, according to our likeness. Take note, God is Spirit and God is Love. As Love He is the source of it. We also know that God is Omnipotent, for He creates out of nothing and He has no beginning and has no end. That means, our love is but a shadow of God's Love. True love looks around to see who is in need of your help, your smile, your possessions, your money, your strength, your quality time. Love forgives and forgets. Love wants for others what it wants for itself. However, true love works in conjunction with other spiritual forces such as patience and faith - in the finished work of our Lord and Savior, Jesus Christ, rather than in what man has done such as science, technology and organizations which won't last forever. To avoid sin and error which leads to the death of your body and your spirit-soul in hell fire (second death), you must make God's Word the standard for your life, not AI or your flesh. If not, God will let you face AI on your own (with your own strength) and it will cast the truth down to the ground, it will be the cause of so much destruction like never seen before, it will deceive many and take many captive in order to enslave them into worshipping it and abiding in lawlessness. We can only destroy ourselves but with God all things are possible. God knows us better because He is our Creater and He knows our beginning and our end. The prove texts can be found in the book of John 5:31-44, 2 Thessalonians 2:1-12, Daniel 2, Daniel 7-9, Revelation 13-15, Matthew 24-25 and Luke 21. *HOW TO MAKE GOD'S WORD THE STANDARD FOR YOUR LIFE?* You must read your Bible slowly, attentively and repeatedly, having this in mind that Christianity is not a religion but a Love relationship. It is measured by the love you have for God and the love you have for your neighbor. Matthew 5:13 says, "You are the salt of the earth; but if the salt loses its flavor, how shall it be seasoned? It is then good for nothing but to be thrown out and trampled underfoot by men." Our spirits can only be purified while in the body (while on earth) but after death anything unpurified (unclean) cannot enter Heaven Gates. Blessed are the pure in heart, for they shall see God [Matthew 5:8]. No one in his right mind can risk or even bare to put anything rotten into his body nor put the rotten thing closer to the those which are not rotten. Sin makes the heart unclean but you can ask God to forgive you, to save your soul, to cleanse you of your sin, to purify your heart by the blood of His Son, our Lord and Savior, Jesus Christ which He shed here on earth because Isaiah 53:5 says, "But He was wounded for our transgressions, He was bruised for our iniquities; the chastisement for our peace was upon Him, and by His stripes we are healed". Meditation in the Word of God is a visit to God because God is in His Word. We know God through His Word because the Word He speaks represent His heart's desires. Meditation is a thing of the heart, not a thing of the mind. Thinking is lower level while meditation is upper level. You think of your problems, your troubles but inorder to meditate, you must let go of your own will, your own desires, your own ways and let the Word you read prevail over thinking process by thinking of it more and more, until the Word gets into your blood and gains supremacy over you. That is when meditation comes - naturally without forcing yourself, turning the Word over and over in your heart. You can be having a conversation with someone while meditating in your heart - saying 'Thank you, Jesus...' over and over in your heart. But it is hard to meditate when you haven't let go of offence and past hurts. Your pain of the past, leave it for God, don't worry yourself, Jesus is alive, you can face tomorrow, He understands what you are passing through today. Begin to meditate on this prayer day and night (in all that you do), "Lord take more of me and give me more of you. Give me more of your holiness, faithfulness, obedience, self-control, purity, humility, love, goodness, kindness, joy, patience, forgiveness, wisdom, understanding, calmness, perseverance... Make me a channel of shinning light where there is darkness, a channel of pardon where there is injury, a channel of love where there is hatred, a channel of humility where there is pride..." The Word of God becomes a part of us by meditation, not by saying words but spirit prayer (prayer from the heart). Take note, God is Spirit and those who worship Him should do so in spirit and truth (genuinely by living the Word). When the Word becomes a part of you, it will by its very nature influence your conduct and behavior. You become a new creation, guided by the Holy Spirit and not just what you hear or see. Your bad habits, you will no longer have the urge to do them. You will think differently, dream differently, act differently and talk differently - if something does not qualify for meditation, it does not qualify for conversation. *THE BATTLE BETWEEN LIGHT AND DARKNESS (GOOD AND EVIL)* Heaven is God's throne and the dwelling place for God's angels and the saints. Hell was meant for the devil (satan) and the fallen angels. Those who torture the souls in hell are demons (unclean spirits). Man's spirit is a free moral agent. You can either yield yourself to God or to the devil because God has given us discretion. If one thinks he possesses only his own spirit, he is lying to himself and he is already in the dark. God is light while the devil is darkness. Light (Holy Spirit) and darkness (evil spirit) cannot stay together in a man's body. God is Love (Love is light) and where there is no love is hell, just as where there is no light is darkness. The one you yield yourself to, you will get his reward. The reward of righteousness to man's spirit is life (abundant life) and the reward of sin to man's spirit is death. Sin and satan are one and the same. Whatever sin can cause, satan also can cause. Sin is what gives the devil dominion or power over man's spirit. When God's Word becomes a part of you, sin power over you is broken, you become the righteousness of God through Christ Jesus. Where Jesus is, you are and when He went (to the Father), you went. In the book of John 8:42-47, Jesus said to them, “If God were your Father, you would love Me, for I proceeded forth and came from God; nor have I come of Myself, but He sent Me. Why do you not understand My speech? Because you are not able to listen to My word. You are of your father the devil, and the desires of your father you want to do. He was a murderer from the beginning, and does not stand in the truth, because there is no truth in him. When he speaks a lie, he speaks from his own resources, for he is a liar and the father of it. Which of you convicts Me of sin? And if I tell the truth, why do you not believe Me? He who is of God hears God’s words; therefore you do not hear, because you are not of God.” My prayer is, "May God bless His Word in the midst of your heart." Glory and honour be to God our Father, our Lord and Savior Jesus Christ and our Helper the Holy Spirit. Watch and pray!... Thank you for your time and may God bless you as you share this message with others.
10 місяців тому
Your tutorials have been sloppy, you rush through everything. You used to explain things slower to people that were new to this.
Get the clothing styles from my Patreon here www.patreon.com/posts/sebs-hilis-79649068
👋
How to change clothes with AI is easy. Show us how to take them off.
Could you make a tutorial creating a custom mask in a photo editing App like Gimp or Photoshop and show how to use in IMG2IMG/Inpainting? I would really appreciate it.. I've searched high-n-low for a detailed tutorial, to NO avail.!!! I'm sure others may find it helpful. Thanx :)
@@SmarthalaylaYou down bad
i'm not able to download the prompt styles
This was a great tutorial!
One point though: when using latent noise as the infill option, you don't retain anything from the original image, it gets overwritten by pure noise.
That's why a low denoising strength didn't work.
It makes sense to always use a denoising strength of 1 when starting from pure noise. Outside of inpainting, when you're generating a new image, it does start from pure noise and denoises it to a final image, so you're just repeating the same process in a smaller area.
FINALLY A1111.
Good tutorial for changing clothes, close to how I do it!
I would recommend using controlnet openpose as well, especially on high denoise inpainting might start to introduce slight differences in the subject's body and pose, so having openpose on the original image keeping the subject in place will save a lot of headache.
Hi can u explain this or is thr amy UA-cam
Thanks! Yeah, I sometimes dig up ControlNet for it, but I find it's mostly for my extreme cases, and not for people learning to use inpainting. Good tip, thank you!
Great tip!
Thanks! And also for using A1111 😊 (Comfy probably very good but for my eyes and usage A1111 is better. Thanks again)
ComfyUI made sense when the workflows were simpler than A1111. Now it's just ridiculous amounts of nodes that take way more effort to set up than using A1111 hence why they're creating websites where people can download the workflows that are then quite messy to tweak or modify, which is basically absurd.
This was a great explanation, thanks Sebastian for clearing up a lot of questions I had about inpainting!
Glad it was helpful!
Another fantastic guide. Great tip with the "s" shortcut for a larger painting area! I used to use Shift+scroll-wheel, but it gets a bit finicky sometimes.
Thanks for you tutorials! This came right on time. I had to change someone's coat and pants. Inpainting did the job!
Trying to help the DinifAI community. Thanks for the tutorial.
How about introducing clothes that are loaded from an image?
Thanks for the video!
Inpaint sketch is a really nice tool to use for something like this as well :) I usually paint the area with the colour I want to use and general shape (as in for example adding a heart necklace), then do Inpaint on the same area to "refine" it :)
You're welcome! Yes, that's a great workflow 🌟🌟
Nice advice, but for some reason my color selector always defaults to a slightly beige peach color. Not sure why. :)
hey can u share me the styles box you have cus mine style box is emty
Instead of generating different pants based on prompt, is it possible to upload a picture of the pant of your choice and ask the model to generate a picture based on the pant picture you uploaded?
Great video! Thanks for the tutorial!
Obviously there are far better and easier ways to do inpainting (and it's been used for a long time to change far more than just clothes), but this is great for someone just starting out!
Which is your preferred a1111 workflow that is better and easier? Would love to hear both your extension and default workflows
not able to download the prompt styles
This is a great tutorial, thanks!
Is there an option to combine outfits from one image and the rest (model, face, pose, hands) from another?
I recall an option with controlnet, not sure about the correct terms. Perhaps scene decomposition? It automatically added tags to certain parts of a scene, like painting or window. Does this exist for people?
It would be nice to create different assets, like faces, hands, hairdos, clothes and rigged human models (perhaps as a set of images from different angles).
If you have these, what is the best way to combine these in a consistent way?
How to do this using ConfyUI? What workflow will it be like? It seems that it can not just drag and drop new image back to the original intuitively.
Great stuff !! Do you think it's possible to input a pillow mockup and a tile pattern texture to wrap on it ?
Thank you,
whats your pc specs
can you share your styles like silk, wool... because i mine box is emty, im a newbie. Thank you so much!!!
Great video, thank you. Sebastian, do you have solution for this problem: when you use Reactor for face-swaps, it works great with photograph style images, but if you try it with a painting-style the swapped face will look too photo-like and does not blend well with rest of the image. Any tips how to adjust it?
Is it possible to change an uploaded image’s style completely with a model from Civitai? For example if the model is to change something into a film noir style etc but without deviating from the original image too much
Use img2img and control net for this. Put your source image in the control net (use open pose/depth/canny models depending on needs) and put your style ref in the img2img input. The style ref doesn't even have to look anything like the model image, it's just for the look.
This workflow will force stable diffusion to keep the structure of your model image but try change it to match the style of the reference image with the aid of your prompt. Then play with the denoise strength till you get what you want.
@@jossipepegonzalez Awesome, thank you for outlining the steps. I'd love to see an example of a pro (like yourself!) doing something like this. :D
@@Kal-el23 haha, hardly a pro, but I know the workflow works. @sebastiankamph actually has a video on exactly this, so he will prob explain it better. The thumbnail is of a lady in the same pose in 3 different styles I think? But another great tool for doing this in a quick and easy way is to use something like "krea" and load an image into the canvas...then just type the new style into the prompt. There are other online platforms that also do these kind of style transfers. Not as customisable and in depth as stable diffusion but sometimes you don't need that level of control, and the tweaking can take a long time. Krea is a real time diffusion engine so the changes you make you can see affect the result as you go, making iterations muuuuch quicker.
Do you happen to know what use cases will allow inpainting models to work? Because most of the time I find inpainting models to be worse than the original model for inpainting so I just deleted them.
Hi. Could you assist me how to preserve the details of graphics on T-shirt? For example, I tried a tshirt with Jurassic park as text with graphic jurassic logo but the result is weird as unreadable text and graphic. How to get to some near to the generation? Thankyou
Can we do inpainting process automatically done and change clothes
Can we use photoshop to do this
you must be skipping a crucial step. I have a t-shirt that I'm trying to change into a sweater. I follow your steps and it remains a t-shirt. My prompts are sleeveless sweater. Shouldn't that work?
Two options: Paint the sleeves on first, then inpaint. Or raise the denoising strength.
this was a great video, is it possible to add an image of a pair of blue jeans to add to the model?
Is there a way to in paint a custom wearable from a photo ?
Hello. I hope you are well. Is there a tool that I can choose the outfit on the model? Other option than any door. It gave me weird results
What about a reference image of clothes?
This explains everything I've been doing wrong. 😂 Thanks, Mr. K!
How can AI be leveraged to create a background for a furniture image in a seamless and aesthetically pleasing manner, considering factors such as lighting, perspective, and style compatibility?
Nice thx. How would you add props like smoking a cigarette? A beer in hand? Etc??
Hi, i am new to this. Is there a tutorial of how to setup stable diffusion. I went to stability ai but i cannot see there how to get to the screen your are showing above. Apreciate any help
You can run it locally on your PC, but you will need about 8GB VRAM minimum. This version is called Automatic1111 and is easy to install. Many guides online
Do you know if I can change the clothes from a still image of an already existing item?
can you do this with Fooocus as well?
how to change masking/inpaint to white brush?
You'd have to use sketch or sketch inpaint to actually paint white.
hello can i put logo without change that cloth?
How can I change the same thing in video
how bout if we have specific image of a clothing already? instead of using prompt
That would be a whole different beast I think. Maybe some combination of IP-adapter or Reference using controlnet, or even some photobashing.
Nice examples but some of them don’t look too realistic. Idk if that is because of the selected model or what. Do you have any suggestions for getting more realistic results ? What’s the difference with keeping on original vs latent noise?
Can I we do same with a photograph instead of a ia generated by stable difussion ?
Sure
@@sebastiankamph Thanks
Or eg how do I copy the outfit from other image and put it in my image
any comfyui workflow for this?
Thanks for the guidance, however we been wondering you should make a video on how to keep the same clothes consistent, that would more useful because AI keeps changing the clothes layout.
How about how to keep the same clothes between different poses?
How about if we want to change to a specific power of outfit from another source ? Does IP adapter work or need to train a new LoRa on the outfit and apply to replace ?
If you don't use Inpaint Models, we need to use Controlnet inpaint right?
what version of SD is this? , also can i use SDXL models on civit ai using v1.7 of SD?
Hi, I have a question for you that might be a good idea for your next content.
I'm new to using Automatic1111 and the file size is getting bigger, around 40GB. I'm using ControlNet and have downloaded the extension or model seg, depth, etc. for ControlNet.
When I use depth and see the preview of the depth image, will it download again in the CMD section? I thought that once I had downloaded parts of ControlNet like depth, seg, etc., it wouldn't download again, but it turns out it still downloads other parts in CMD. This also applies to extensions. Is that how it works? Or will it only download the remaining parts in CMD when using depth, etc. for the first time?
how well does inpainting work with SDXL checkpoints? great video:)
Wouldn't it be more suitable to use the sketch mode in general if one wants clothes in different colors. So in this case not only for the hat but for top and bottom clothes too?
It would, but I wanted to show different workflows. But if you want to change colours in general, use sketch.
Can you elaborate on why sketch is better?
Definitely an amazing tutorial. Thanks for sharing.
I would rather use stylar extension, it just takes few clicks.
Is it possible to upload an other photo from which we want to copy the outfit?
I guess if you put together a more advanced workflow. But this is the million dollar question that all companies want to solve right now 😂
Now show me how to keep the same clothing from scene to scene
Why are clocks different from AI images? They have the right amount of hands.
While I knew this it reminded me that I really need to use inpainting more to fix and add to images. Cheers.
Ooh, that's a new joke for new times. Nice.
what is the name of the program?
Hi Seb, how do you organize your styles?
Hey, how do you mean? I have them in a styles.csv available for download in my Patreon.
I mean with these style separations@@sebastiankamph
how to run without nvidia graphic please
do i need strong pc for this?
Kind of. Gpu 4gb+
I was thinking: Is it possible I take a picture of my friends clothes and using stable diffusion move these clothes to my picture? like I dressed with these clothes without distort or change any part of clothes?
I'm not 100% certain but I don't think so....not the way you describe. You could load the image of yourself, mask an area and then describe your friends clothes. That would work to some degree, depending on what your friend is wearing.
I mean you could photobash them on top and then inpaint, but they would change a little.
thanks Sebastian
You got it!
That’s cool, although I’m looking how to apply consistent clothing to my character. So, if I’m going to give them a white crop top, then I want it to be a crop top of a specific style with a specific design to it. If I’m going to give them a red hat, I want it to be a red hat that looks a specific way. Most of the time, when I change my character’s clothes, I want it to be clothes within their wardrobe, rather than random clothes. I wonder if there’s currently any way to maintain consistency in clothing.
I find it its only possible with lora that is trained on one piece of clothing, still AI by feature love to change it
Tjena Sebastian! Bra och informativa klipp. Kan du lära mig hur man spelar in sin röst för att använda i videos (text to speech)?
sir do you use google collab?
No, I wouldn't recommend google colabs anymore. Easier to just use cloud solutions like ThinkDiffusion if you don't have a gpu.
@@sebastiankamph sir I have amd rx 6700xt is it possible to run on that I am unable to find any solution
@@transporter3231 Yes, but not easy. Most don't support amd natively. Linux can manage it easier I believe. If you don't want to go through the amd mess of stable diffusion, I would just get a nvidia or use cloud solutions.
@@sebastiankamph sir what is the best free cloud option available?
This doesn't work. I mask off the area and enter my prompt and it just ignores it, making the same image again. Yes, I have mask only checked.
Check your denoising strength
Yay Auto!! Nowadays nobody cares about Auto users. Thank you for doing this mate. 💛
Thank you so much for creating all these amazing tutorials and not buying into the ridiculous ComfyUI meme like other creators.
I stack 2 jokes before I stack 2 jokes
And then I stack 2 more
amazing!
Can we do it on video?
Hello may I know your pc specs? 😆
Hey, I use an rtx 4090 :)
@@sebastiankamph woow
Isn't it better to do in Photoshop? With new IA of recreative you can do it maybe even better
please make one where we can create images with our own avatar, dreambooth, IP adapter etc with the latest tech
For that purpose it is better to use new face id ip-adapter, it can make amazing avatars.
Sampling steps only 20, I would expect more is needed for details?
Depends on the sampler. I usually stick with 25-30 and rarely go past it tbh.
Cheers 🥂
I have also noticed that using "whole picture" changes how the AI responds to prompts. It actually seems to consider the entire image as part of what it's trying to generate if you go with "whole picture," while it will ignore the unmasked portion in considering what it's trying to generate if you do "masked only."
For example, if you want to give Doctor Strange a third eye in his forehead, some models will utterly refuse to put three eyes onto a person; it will keep just making weird smudges where you inpainted for that eye. But if you do "masked only," it will ignore that there are eyes on the face already, and generate an eye where you put the mask.
So, if you have a stubborn model and don't know a better one to use for what you're trying to do, "masked only" can help you force changes. On the other hand, if you want to ensure that whatever you're doing fits in with the rest of the image, by being considered as part of the whole, "whole picture" helps a lot with that.
big fan
Wow, thank you! :)
Your PC specs
Rtx 4090
@@sebastiankamphthank you
One more question ❓
. can you tell me best to easy way Train realistic lora
Tack så mycket!!
Thank you!
Is UA-cam your part-time job?
im sad my stabble is so old lol
Can you also do a tutorial on comfyui? :(
When I write it as a dress, it does it from scratch with a human:( not only a dress is added, but people are also added:(
same issue here! Sometimes miniature humans at the size of the mask (for instance, a person wearing pants, or vanished pants). Also, in my case, other times it generates incomplete objects or vanished ones. I woukd like to know why because inpainting on Foocus and ComfyUI works great and quick, but man I want to like A1111 and try to understand why generates garbage results.
Your denoise value is too high, so the original content is not being respected. For original text2img we usually use about 0.75, but for inpainting small areas, you can use much lower (maybe 0.30). OR, and this is better: use pose controlnet-- then you can use higher denoise without losing the original composition.
changing the clothes is no problem keeping the same clothing thats the problem
How to remove clothes
Get help
@@Blackmamba_yellowfit already did it are you jealous?
@@MewTube-o4l as long as you keep your creepiness directed to fake women.
👍👍👍👍👍
Hahaha that last red hat! Looked like a potato!
Lovely red leather potato!
This is a great video. Thank you! Could you do a similar video for inpainting in ComfyUI? And do both SDXL and SD1.5?
Let's be honest here. We are not looking to add any clothing at all to the pictures we are working on LMAO!
batch??? same pictures??? ah no....
*/• I believe we are meant to be like Jesus in our hearts and not in our flesh. But be careful of AI, for it knows only things of the flesh such as our fleshly desires (without fear of God) and cannot comprehend things of the Spirit such as true love and eternal joy that comes from obeying God's Word [Galatians 5:16-26]. Man is a spirit and has a soul but lives in a body which is flesh. When you go to bed it is the flesh that sleeps, but your spirit never sleeps and that is why you have dreams, unless you have died in peace physically. More so, true love that endures and last is a thing of the heart. When I say 'heart', I mean 'spirit'. But fake love, pretentious love, love with expectations, love for classic reasons, love for material reasons (love because of material needs) and love for selfish reasons outside God those are things of the flesh. In the beginning God said let us make man in our own image, according to our likeness. Take note, God is Spirit and God is Love. As Love He is the source of it. We also know that God is Omnipotent, for He creates out of nothing and He has no beginning and has no end. That means, our love is but a shadow of God's Love. True love looks around to see who is in need of your help, your smile, your possessions, your money, your strength, your quality time. Love forgives and forgets. Love wants for others what it wants for itself. However, true love works in conjunction with other spiritual forces such as patience and faith - in the finished work of our Lord and Savior, Jesus Christ, rather than in what man has done such as science, technology and organizations which won't last forever. To avoid sin and error which leads to the death of your body and your spirit-soul in hell fire (second death), you must make God's Word the standard for your life, not AI or your flesh. If not, God will let you face AI on your own (with your own strength) and it will cast the truth down to the ground, it will be the cause of so much destruction like never seen before, it will deceive many and take many captive in order to enslave them into worshipping it and abiding in lawlessness. We can only destroy ourselves but with God all things are possible. God knows us better because He is our Creater and He knows our beginning and our end. The prove texts can be found in the book of John 5:31-44, 2 Thessalonians 2:1-12, Daniel 2, Daniel 7-9, Revelation 13-15, Matthew 24-25 and Luke 21.
*HOW TO MAKE GOD'S WORD THE STANDARD FOR YOUR LIFE?*
You must read your Bible slowly, attentively and repeatedly, having this in mind that Christianity is not a religion but a Love relationship. It is measured by the love you have for God and the love you have for your neighbor. Matthew 5:13 says, "You are the salt of the earth; but if the salt loses its flavor, how shall it be seasoned? It is then good for nothing but to be thrown out and trampled underfoot by men." Our spirits can only be purified while in the body (while on earth) but after death anything unpurified (unclean) cannot enter Heaven Gates. Blessed are the pure in heart, for they shall see God [Matthew 5:8]. No one in his right mind can risk or even bare to put anything rotten into his body nor put the rotten thing closer to the those which are not rotten. Sin makes the heart unclean but you can ask God to forgive you, to save your soul, to cleanse you of your sin, to purify your heart by the blood of His Son, our Lord and Savior, Jesus Christ which He shed here on earth because Isaiah 53:5 says, "But He was wounded for our transgressions, He was bruised for our iniquities; the chastisement for our peace was upon Him, and by His stripes we are healed". Meditation in the Word of God is a visit to God because God is in His Word. We know God through His Word because the Word He speaks represent His heart's desires. Meditation is a thing of the heart, not a thing of the mind. Thinking is lower level while meditation is upper level. You think of your problems, your troubles but inorder to meditate, you must let go of your own will, your own desires, your own ways and let the Word you read prevail over thinking process by thinking of it more and more, until the Word gets into your blood and gains supremacy over you. That is when meditation comes - naturally without forcing yourself, turning the Word over and over in your heart. You can be having a conversation with someone while meditating in your heart - saying 'Thank you, Jesus...' over and over in your heart. But it is hard to meditate when you haven't let go of offence and past hurts. Your pain of the past, leave it for God, don't worry yourself, Jesus is alive, you can face tomorrow, He understands what you are passing through today. Begin to meditate on this prayer day and night (in all that you do), "Lord take more of me and give me more of you. Give me more of your holiness, faithfulness, obedience, self-control, purity, humility, love, goodness, kindness, joy, patience, forgiveness, wisdom, understanding, calmness, perseverance... Make me a channel of shinning light where there is darkness, a channel of pardon where there is injury, a channel of love where there is hatred, a channel of humility where there is pride..." The Word of God becomes a part of us by meditation, not by saying words but spirit prayer (prayer from the heart). Take note, God is Spirit and those who worship Him should do so in spirit and truth (genuinely by living the Word). When the Word becomes a part of you, it will by its very nature influence your conduct and behavior. You become a new creation, guided by the Holy Spirit and not just what you hear or see. Your bad habits, you will no longer have the urge to do them. You will think differently, dream differently, act differently and talk differently - if something does not qualify for meditation, it does not qualify for conversation.
*THE BATTLE BETWEEN LIGHT AND DARKNESS (GOOD AND EVIL)*
Heaven is God's throne and the dwelling place for God's angels and the saints. Hell was meant for the devil (satan) and the fallen angels. Those who torture the souls in hell are demons (unclean spirits). Man's spirit is a free moral agent. You can either yield yourself to God or to the devil because God has given us discretion. If one thinks he possesses only his own spirit, he is lying to himself and he is already in the dark. God is light while the devil is darkness. Light (Holy Spirit) and darkness (evil spirit) cannot stay together in a man's body. God is Love (Love is light) and where there is no love is hell, just as where there is no light is darkness. The one you yield yourself to, you will get his reward. The reward of righteousness to man's spirit is life (abundant life) and the reward of sin to man's spirit is death. Sin and satan are one and the same. Whatever sin can cause, satan also can cause. Sin is what gives the devil dominion or power over man's spirit. When God's Word becomes a part of you, sin power over you is broken, you become the righteousness of God through Christ Jesus. Where Jesus is, you are and when He went (to the Father), you went. In the book of John 8:42-47, Jesus said to them, “If God were your Father, you would love Me, for I proceeded forth and came from God; nor have I come of Myself, but He sent Me. Why do you not understand My speech? Because you are not able to listen to My word. You are of your father the devil, and the desires of your father you want to do. He was a murderer from the beginning, and does not stand in the truth, because there is no truth in him. When he speaks a lie, he speaks from his own resources, for he is a liar and the father of it. Which of you convicts Me of sin? And if I tell the truth, why do you not believe Me? He who is of God hears God’s words; therefore you do not hear, because you are not of God.” My prayer is, "May God bless His Word in the midst of your heart." Glory and honour be to God our Father, our Lord and Savior Jesus Christ and our Helper the Holy Spirit. Watch and pray!... Thank you for your time and may God bless you as you share this message with others.
Your tutorials have been sloppy, you rush through everything. You used to explain things slower to people that were new to this.
You're probably correct in that they're quicker. Not sloppy though, takes more work this.
can u take off the clothes? asking for a freind
It looks like In invoke AI this is much more intuitive. Fortunately we have better ways tu utilize stable diffusion than Automatic 1111
I agree, there are many tools that focus more on UI and UX. The results of a1111 inpainting are hard to beat though.
no love for comfy :(