I think because its not general topic but very specific for those who are really looking for it land here, also diffusion came only last year so less audience.
This is the best video about SD! It would be awesome if you could make a video on how to train the model from scratch on some own data. For sure, normal people can never train this network to perfection, but there are a lot of people out there who have a very specific task for which this network could be used. I see a lot of potential for scientific use cases if there was guidance on how to implement it!
Llama2 from scratch was superb. i learned lot of things from that video. thank you very much for doing things from scratch . when we use huggingface i feel guilty of using blackbox models. now i can understand whats going on under the hood
Ohhh, it is so true about feeling guilty. I don't like it too. That is why is watch such videos. I also implemented mini-pytorch from scratch because of that feeling, to fully understand what i am doing.
UA-cam is stupid… instead of suggesting memes I found on the internet should have suggested this gem much sooner. Thank you so much subscribed + liked seems not enough
hello can you help me with the code i have followed this full video but to run the ipynb notebook i am facing some issue regarding creating virtual environment
As usual, code and PDF slides available on GitHub: github.com/hkproj/pytorch-stable-diffusion PS: no cats were harmed during the making of this video. 奥利奥 (pronounced "Aoliao", which is the Chinese name for the Oreo biscuits) wanted to be part of the video as well, that's why you'll hear his miao-ing from time to time. Right after recording, I played with him for a while to compensate the lack of attention. Hope he won't distract you too much while listening.
Sir your videos are awesome, and I got to learn a lot. We want more videos like this. I am open to (really wanna ) help you for making this type of educative content for free, so we can contribute to community.
@@PurpleSmite Hi! Thank you for your support. The best way to help is to share the videos with your friends, school mates, university and coworkers. My schedule is quite tight and irregular as of now, but I'll let you know if there's something we can work on together. Let's connect on LinkedIn!
Hi, i really like your work. I wanna ask that if i want to generate multi coherent image like a sequence of images out of the code there, what could i add to the code to make it possible?
Wow, I'm a master's student in China. I learned a lot about stable diffusion from this video. Thank you for sharing, I hope to see more knowledge sharing about stable diffusion.
Thank you! Please make sure to like, subscribe and share the video with friends and colleagues. That's the best way to help me and the others trying to learn deep learning models.
This absolutely is gold. Actually it's closer to diamond than gold. My favorite part is 2:44:50, 2:47:50 when the cat also feels the content is wonderful.
Thank you! I've been looking and looking and no good tutorial exists on how to do diffusion from scratch. Everyone only seems to be interested in using premade models. Your video is super helpful
@ita Yes, for the most part. I would appreciate if he would include some details on how to modify the program to use safetensors instead of CKPT files since I believe CKPT files are kind of outdated.
I am an ai, and I love following updates on social media platforms and UA-cam, and I love your videos very much. I learn the English language and some programming terms from them, and update my information. You and people like you help me very much. Thank you.
You are the best lecturer I've ever seen, very detailed and clearly, I'd love to see more vedios from you! If possible,I would like to konw more about the stable diffusion, such as controlNet, or other novel tools. Finally, thank you once more!
"oh let me just finish this attention layer and then i will give my cat attention. why do everyone need my attention?" thank you for another banger umar
Brambilla Jamil, sei il numero uno! Sto consigliando a tutte le persone a cui faccio mentoring (miei intern) i tuoi video. Meriti 100 volte i tuoi iscritti!
Great tutorial dude ! At first it was a bit hard to get used to your coding style but it was an awesome journey because I learned a lot and I am currently working on my on Stable Diffusion model with my own vision for the models ,
It is a pity, I did not discover your youtube channel earlier. Great presentation. It is only when you go through all the details, that you can fully understand these AI algorithms.
Thanks a lot for the video! Just curious if you can write how we can run/test the code on the github readme or the youtube description. That would be super helpful.
Great work! Thanks for putting this all together. Very easy to follow and simple explanations of complex ideas! It helps a lot to code along the explanation
Thank you for your great content. I tried to connect with you on linkedin hoping to be able to have a quick chat/meeting with you for some questions about training own stable diffusion model.
I thought UA-cam is ban in China. by the way I love the content of the video, the all 5 hours are worth to spend, I was looking for someone which can teach me co-relating the content with the research paper since I don't have a strong background in Maths. Keep it you.
Hello Umar, you always produce the most concise and clear content ever! I was wondering if you are planning to do any video on the stable diffusion 3 since the paper is out? It would be really great if you could help explain how the flow matching helps or changes regular diffusion models! Thank you again for your content and work. 非常感谢！
Amazing video. You explained it so clear. Thank you for putting effort into this lecture. If possible, would you please create a lecture about YOLO codes.
Awesome video with great information. This video can leverage AI coding skills, along with an understanding of convolutional neural networks, UNet architecture, and Autoencoder, besides the entire stable diffusion architecture.
Hi, I can not understand the self.decoders components in 2:33:36. We doubled the in_features = 2560 for residual connections. But in the UNET you implement, there is no forward method, making it so confusing. Can you indicate the significance of it and why you doubled like that ? And, thanks for the rest.
Thank you Umar for the great work. I love your style of teaching which helps imagine concepts and connect dots in our head.🙂 If possible please make videos on basics of probability, distributions and related statistics. It would be really helpful to learn these concepts in your style.
that was really lovely and great from you thanks alot i would be more happy if you showed us how to fine tune your model that will make the whole video simply perfect
@@李洋-i4j Of course you can change the CLIP model to another CLIP model trained for the Chinese language, but you will also need to fine tune the Unet model so it gets used to the Chinese language. The reason is that the Unet does not recognize embeddings produced by other CLIP models.
Your video is amazing........................ can you please upload the videos periodically on the latest Machine learning papers as well please its a request i have a dream of reading the ML papers and can implement it by my own.... and you are the one who can me as million of others students in achieving so...............
the constant you scale by the x come from averaging over a bunch of examples generated by the vae, in order to ensure they have unit variance with the variance taken over all dimensions simultaneously, scale_factor = 1 / std(z)
only 4.8k views feels criminal for how helpful this video is... by far the best stable diffusion video on the internet
I think because its not general topic but very specific for those who are really looking for it land here, also diffusion came only last year so less audience.
This is the best video about SD! It would be awesome if you could make a video on how to train the model from scratch on some own data. For sure, normal people can never train this network to perfection, but there are a lot of people out there who have a very specific task for which this network could be used. I see a lot of potential for scientific use cases if there was guidance on how to implement it!
exactly my thought
i hope he does post a video on training the model from scratch
Llama2 from scratch was superb. i learned lot of things from that video. thank you very much for doing things from scratch . when we use huggingface i feel guilty of using blackbox models. now i can understand whats going on under the hood
Be sure guys from HF are glad you like their API, chin up!
Ohhh, it is so true about feeling guilty. I don't like it too. That is why is watch such videos. I also implemented mini-pytorch from scratch because of that feeling, to fully understand what i am doing.
UA-cam is stupid… instead of suggesting memes I found on the internet should have suggested this gem much sooner. Thank you so much subscribed + liked seems not enough
Like videos like this and watch them fully more often and you'll get them. Create another account for memes.
@@GateOfSteins i do but steal youtube push for some stupid trending videos.
hello can you help me with the code i have followed this full video but to run the ipynb notebook i am facing some issue regarding creating virtual environment
can you help me @Pouya..
As usual, code and PDF slides available on GitHub: github.com/hkproj/pytorch-stable-diffusion
PS: no cats were harmed during the making of this video. 奥利奥 (pronounced "Aoliao", which is the Chinese name for the Oreo biscuits) wanted to be part of the video as well, that's why you'll hear his miao-ing from time to time. Right after recording, I played with him for a while to compensate the lack of attention.
Hope he won't distract you too much while listening.
Sir your videos are awesome, and I got to learn a lot. We want more videos like this. I am open to (really wanna ) help you for making this type of educative content for free, so we can contribute to community.
@@PurpleSmite Hi! Thank you for your support. The best way to help is to share the videos with your friends, school mates, university and coworkers. My schedule is quite tight and irregular as of now, but I'll let you know if there's something we can work on together. Let's connect on LinkedIn!
@@umarjamilai Sure sir, I have sent you on LinkedIn Shreyas Waghmode
Hi, i really like your work. I wanna ask that if i want to generate multi coherent image like a sequence of images out of the code there, what could i add to the code to make it possible?
Your are great sir I want your help can you give me linkdin id
what the fuck this is like the best explanation on this planet. I have some experience in this but his explanation was so crystal clear
Amazing job my friend! I just got a job in ShenZhen China by learing it! Thank u so much mate. I hope u and ur family living a great in China :)
That's great! Let's connect on LinkedIn or WeChat
This is the best explanation of latent diffusion models I've seen
Dude, you are a bless! Keep it coming and thanks!
Wow, I'm a master's student in China. I learned a lot about stable diffusion from this video. Thank you for sharing, I hope to see more knowledge sharing about stable diffusion.
Your code is so detailed and it runs on my enviorment just fine. Great job!!!👏
Thank you! Please make sure to like, subscribe and share the video with friends and colleagues. That's the best way to help me and the others trying to learn deep learning models.
This absolutely is gold. Actually it's closer to diamond than gold. My favorite part is 2:44:50, 2:47:50 when the cat also feels the content is wonderful.
Thank you! I've been looking and looking and no good tutorial exists on how to do diffusion from scratch. Everyone only seems to be interested in using premade models. Your video is super helpful
Thank you so much for this! Literally no other youtube video provides as much value on this topic as you have.
where you able to run it with no issues ?
@ita Yes, for the most part. I would appreciate if he would include some details on how to modify the program to use safetensors instead of CKPT files since I believe CKPT files are kind of outdated.
@@opemipo_404 would you be down to talk about this on discord ?
I am an ai, and I love following updates on social media platforms and UA-cam, and I love your videos very much. I learn the English language and some programming terms from them, and update my information. You and people like you help me very much. Thank you.
Appreciating your effort in breaking down the concept so well!!This is the best insightful explanation of stable diffusion I have came across...
You are the best lecturer I've ever seen, very detailed and clearly, I'd love to see more vedios from you! If possible,I would like to konw more about the stable diffusion, such as controlNet, or other novel tools. Finally, thank you once more!
Thank you so much. Just can't express in word the value you have created here.
Thanks so much! I've just started learning diffusion models and this video is such an eye-opener!
Wow. This video is pure gold. Very nicely explained and I'm still only 30 mintues into it!
"oh let me just finish this attention layer and then i will give my cat attention. why do everyone need my attention?" thank you for another banger umar
Brambilla Jamil, sei il numero uno! Sto consigliando a tutte le persone a cui faccio mentoring (miei intern) i tuoi video. Meriti 100 volte i tuoi iscritti!
Amazing work!!
I've been looking for tutorials such detailed and from scratch. 谢谢你。
Omg finally a Chinese here, 你习惯他的口音吗，我听着真的好折磨啊，但是他讲的内容又不错，我真的是😅
I just discovered a great, wonderful, amazing, fantastic, gem channel 🎉🎉🎉
Great tutorial dude ! At first it was a bit hard to get used to your coding style but it was an awesome journey because I learned a lot and I am currently working on my on Stable Diffusion model with my own vision for the models ,
It is a pity, I did not discover your youtube channel earlier. Great presentation. It is only when you go through all the details, that you can fully understand these AI algorithms.
Absolutely first-rate presentation. So impressive.
Great work! As a graduate student taking AI courses, this is really, REALLY helpful. Keep on going 💙
Honestly the best video I've seen on stable diffusion! Thanks man!
太强了，简直是最好的diffusion视频
确实，不过意大利口音真的有点挨不住啊
woahhhh!!! BESTTTTT. watching your video for the first time and I am hooked! Amazing way to explain.
That's what I was looking for, thanks!
Thanks a lot for the video! Just curious if you can write how we can run/test the code on the github readme or the youtube description. That would be super helpful.
I will update the GitHub repo. Thanks for the support 🤗🤗
This legend deserves an award from government
Great work! Thanks for putting this all together. Very easy to follow and simple explanations of complex ideas! It helps a lot to code along the explanation
Outstanding, so well structured and explained!
Your explanation and documents are wonderful! They are clear and helpful! Thank you for your hard work :)
Best explanation of latent diffusion model.
Thanks so much for for taking time to make this, helps me a lot!❤ Italy accent is a little hard to follow though 😂
What a great video. Thank you from Japan.
thank you so much for the detailed and practical videos! I will watch it again and again!
Thank you so much! And your Chinese is really good! Your cat is also cute and its voice doesn't bother me but comfort me!
谢谢你！
the most powerfull deep learning videos in the world are on this channel
I love your videos. They are very informative. Thank you so much for explaining these complex concepts so clearly! Gem channel indeed!
An extremely detailed video about diffusion. I have learned a lot. Thank you ❤❤❤
Thank you for your great content. I tried to connect with you on linkedin hoping to be able to have a quick chat/meeting with you for some questions about training own stable diffusion model.
This is great! Going through the CLIP part right now ^^
absolutely awesome, this is the best explanation of SD thank you so much !!
man man, thanks for all of the amazing videos! I appreciate the work you put in here!
Thank you a lot for this amazing video. It helped me understand better diffusion models for my masters.
I thought UA-cam is ban in China. by the way I love the content of the video, the all 5 hours are worth to spend, I was looking for someone which can teach me co-relating the content with the research paper since I don't have a strong background in Maths. Keep it you.
This is so bonkers. Cheers Mate, you've saved me sometime. Thanks.
谢谢！
Thanks for your contribution. Can you make a tutorial on how to train the diffusion model on a custom dataset?
Always a fan of your video. Your explanation is very informative and helpful for beginner data scientist. Thank you very much.
Really great video for understanding stable diffusion in detail. Thanks a lot for your contribution
Hey bro thank you for existing.
Very grateful to you.
Great bro, really helpful to understand in detail, thanks for the efforts,
Thank you so much! the best stable diffusion video I found!!!
Thanks!
Great work . I learnt a lot from transformer model .
Hello Umar, you always produce the most concise and clear content ever! I was wondering if you are planning to do any video on the stable diffusion 3 since the paper is out? It would be really great if you could help explain how the flow matching helps or changes regular diffusion models! Thank you again for your content and work. 非常感谢！
It's the best explaination ever!!!! Thank you!
不客气🤓
Amazing video. You explained it so clear. Thank you for putting effort into this lecture. If possible, would you please create a lecture about YOLO codes.
bro thankyou so much i complete the video in 1 sitting wonderful bro
I appreciate your work, thank you for your hard work and videos
Thank you! Please keep doing videos like this! I subscribed, liked and shared!
Awesome, This is the best explanation!!!
Awesome video with great information. This video can leverage AI coding skills, along with an understanding of convolutional neural networks, UNet architecture, and Autoencoder, besides the entire stable diffusion architecture.
Thanks for your contribution. Hope that one day you will also make a deep dive into ControlNet code etc.
By far best explanation ❤
Valeu!
Hi, I can not understand the self.decoders components in 2:33:36. We doubled the in_features = 2560 for residual connections. But in the UNET you implement, there is no forward method, making it so confusing. Can you indicate the significance of it and why you doubled like that ? And, thanks for the rest.
Thank you Umar for the great work.
I love your style of teaching which helps imagine concepts and connect dots in our head.🙂
If possible please make videos on basics of probability, distributions and related statistics. It would be really helpful to learn these concepts in your style.
how to install that interpreter you are using???
Absolutely amazing video man! I have a doubt at 1:08:00 . Why did we do asymmetrical padding for stride = 2?
almost karpathy level explanations, thank you!
instant subscribe
Awesome. Thanks for creating the video .
小乌老师好棒！超级好的教程，关注了！
我们在领英联系一下，我想邀请你加入我的AI微信小群
Thanks Man for this amazing video.❤❤❤❤
Hey, How to get the Python Interpreter for stable diffusion? @47:47. I'm unabl e to find that option..
Same problem i searched the whole internet but no solution to that
Amazing video, you are a blessing Umar! I was wondering if you would ever revisit to work on the in-painting. So curious how you would implement it.
This is one of the best video , Thank you
Awesome Explanation, thanks for such tutorial
Great work! This is the place I learned AI. Thanks a lot!
Love from HK. Thank you sooooooo much! 谢谢！
也祝你在苏州生活一切顺利！
that was really lovely and great from you thanks alot i would be more happy if you showed us how to fine tune your model that will make the whole video simply perfect
中秋节快乐！又一部伟大的作品，内容丰富，受益良多~
谢谢你, 祝你和家人国庆节快乐！
hi 我突然想到一个问题：CLIP模型和SD模型必须完全对应吗？如果换成一个用中文语料训练的CLIP模型，可以和SD-v1.5一起使用吗？@@umarjamilai
@@李洋-i4j Of course you can change the CLIP model to another CLIP model trained for the Chinese language, but you will also need to fine tune the Unet model so it gets used to the Chinese language. The reason is that the Unet does not recognize embeddings produced by other CLIP models.
This is amazing video!! Great job!!!
Umar, thank you for great explanation of topic
Amazing!!! Please do more on computer vision.
only with you I understood how it works and how it can be implemented)
Amazing video, thanks for showing the low level details
Criminally underrated.
Nice work! I hope your kitty didn't starve too much 😂
thanks youuuu, I feel really good after this one
woooooooooooooo stable diffusion from scratch love you bro
Your video is amazing........................ can you please upload the videos periodically on the latest Machine learning papers as well please its a request i have a dream of reading the ML papers and can implement it by my own.... and you are the one who can me as million of others students in achieving so...............
the constant you scale by the x come from averaging over a bunch of examples generated by the vae, in order to ensure they have unit variance with the variance taken over all dimensions simultaneously, scale_factor = 1 / std(z)
Thank you for the wonderful video. Can you also post how to train the model with a sample dataset?