Diffusion Models Explained : From DDPM to Stable Diffusion

  Рет қаралды 7,352

Martin Andrews

Martin Andrews

Күн бұрын

Пікірлер: 15
@taherehtoosi9869
@taherehtoosi9869 7 ай бұрын
Very clear explanation, I recommended your channels to friends who want to catch up with recent developments in AI.
@Omsip123
@Omsip123 4 ай бұрын
Very interesting and well explained, thanks a lot for your efforts
@ArunReddyAnugu
@ArunReddyAnugu 11 ай бұрын
Thanks a lot, the talk covered all the topics i wanted to know.
@mattkkma
@mattkkma Жыл бұрын
Excellent coverage of a large topic. Cheers
@scskowron
@scskowron 5 ай бұрын
Thank you for the explanation. It does seem like you mixed up the diffusion processes though. At 2:50 you refer to the process of adding noise as the backwards process, and removing noise as the forward process. In section 2 of the DDPM paper, they define the reverse process as starting with noise, and the forward process as the one where Gaussian noise is added.
@jeangatti9384
@jeangatti9384 7 ай бұрын
Very nice informative vid, and for once a teacher who speaks clearly and quietly 👍
@TheArtonator
@TheArtonator Жыл бұрын
Thank you so much! I am getting into stable diffusion, I learned so much about it.
@JBoy340a
@JBoy340a 2 жыл бұрын
Martin. Great job organizing this fast changing area!
@MartinAndrews-mdda
@MartinAndrews-mdda 2 жыл бұрын
Thanks! I originally thought that just a historical retelling might be a bit dry, but in this case the new ideas clearly developed as the topic ping-ponged between several research labs. So the explanation, coupled with the 'race', seemed like a good fit :-)
@saminchowdhury7995
@saminchowdhury7995 Жыл бұрын
​@@MartinAndrews-mdda you did so well sir. It's not easy to be so clear and concise when explaining such a complex space. You are very talented
@postdaigo
@postdaigo 2 жыл бұрын
Amazing video! Thank you so much for taking your time to do it!
@MartinAndrews-mdda
@MartinAndrews-mdda 2 жыл бұрын
Great comment! Thank you so much for taking your time to make it! Genuinely appreciated :-)
@postdaigo
@postdaigo Жыл бұрын
@@MartinAndrews-mdda Do you plan on making a follow-up on this? With ControlNet, LoRA, etc. Also, is there a place where I can watch your other MLSG presentations?
@sgsrules
@sgsrules 2 жыл бұрын
Great video, thanks for sharing this talk. Being able to tile images using stable diffusion is not a niche function, it's incredibly useful for artists generating textures for 3d models. This will be one of the biggest use cases for this tech in it's current state. Also that's probably not a pixie... that's Link from the Legend of Zelda, you're obviously not a gamer lol.
@MartinAndrews-mdda
@MartinAndrews-mdda 2 жыл бұрын
Only gaming I do is Minecraft :-) So perhaps I shouldn't have made such a big deal of how 'niche' the tileable thing was... Good catch identifying the pixie!
PaperView: Denoising diffusion probabilistic models
1:00:12
Shayan Fazeli
Рет қаралды 7 М.
Quando A Diferença De Altura É Muito Grande 😲😂
00:12
Mari Maria
Рет қаралды 45 МЛН
Cheerleader Transformation That Left Everyone Speechless! #shorts
00:27
Fabiosa Best Lifehacks
Рет қаралды 16 МЛН
Mom Hack for Cooking Solo with a Little One! 🍳👶
00:15
5-Minute Crafts HOUSE
Рет қаралды 23 МЛН
Stable Diffusion in Code (AI Image Generation) - Computerphile
16:56
Computerphile
Рет қаралды 297 М.
How AI 'Understands' Images (CLIP) - Computerphile
18:05
Computerphile
Рет қаралды 219 М.
Why Does Diffusion Work Better than Auto-Regression?
20:18
Algorithmic Simplicity
Рет қаралды 399 М.
All Machine Learning algorithms explained in 17 min
16:30
Infinite Codes
Рет қаралды 434 М.
What are Diffusion Models?
15:28
Ari Seff
Рет қаралды 240 М.
Learn Machine Learning Like a GENIUS and Not Waste Time
15:03
Infinite Codes
Рет қаралды 237 М.
High-Resolution Image Synthesis with Latent Diffusion Models
47:50
ChatGPT : How it works and what's coming next for Large Language Models
48:45
How I Understand Diffusion Models
17:39
Jia-Bin Huang
Рет қаралды 39 М.