The Absurd Evolution of The Current Best Video Generator

Рет қаралды 18,598

Күн бұрын

Пікірлер: 65

@bycloudAI 3 ай бұрын

You can try out Luma AI's Dream Machine here! luma.1stcollab.com/bycloudai I am really good at having great timing. MovieGen came out when I nearly finished the video. I'm sad. So here's a quick definition of DiT: A diffusion transformer (DiT) is a model that combines elements of diffusion models and transformers to generate data like image synthesis, audio generation, or text generation. Diffusion models are a class of probabilistic generative models that create data by iteratively denoising a latent variable, which starts from pure noise and is gradually transformed into a coherent sample. Transformers on the other hand, are neural network architectures known for their ability to model long-range dependencies in data, primarily through self-attention mechanisms. You could ultimately say that, a diffusion transformer is just a transformer with the goal of denoising. Yum. Here's MovieGen's paper: arxiv.org/abs/2410.13720 it contains a better run down to crafting the latest near SoTA video generation

@El_Carlangas 3 ай бұрын

Thanks a lot for this video, it was really helpfull to start to understand how all these ai technology works. All the people working behind this is literal geniuses.

@diogonunes1608 3 ай бұрын

The baking analogy was perfect for me. Thank you 🙏😊

@tannenbaumxy 3 ай бұрын

Yes, a deep dive into diffusion transformers for one of the next videos would be awesome!

@cdkw2 3 ай бұрын

that bread analogy really got me hooked, nice work and animation!

@DJTechnosapien 3 ай бұрын

Hey man, really appreciate your humor and memes, makes learning ML a lot more fun. Always looking forward to more!

@MilesBellas 3 ай бұрын

A video on Diffusion Transformers = 😊👍

@m_e_m_es4649 3 ай бұрын

Could you possibly make the same video for Openai's advanced voice mode?

@Words-. 3 ай бұрын

I second this

@authenticallysuperficial9874 3 ай бұрын

Upvote

@sammonius1819 3 ай бұрын

I'm pretty sure they trained an AI to mimic text-to-speech conversations between people and GPT-4, and then fine-tuned it on actual human speech to make it sound more natural. That would explain why it sounds uncanny rather than robotic or human. Just my guess though.

@nilaier1430 3 ай бұрын

Hey, bycloud, even if you fell off, I won't stop watching your nerdy videos because they're cool ❤

@thenoblerot 3 ай бұрын

Yes please, a video on diffusion transformers! Great channel

@rmt3589 3 ай бұрын

We definitely need a dedicated video.

@andrey2001v 3 ай бұрын

This video is so cool, a literal gold mine of information on how modern AI models work Bread analogy was extra nice - I finally understand why diffusion models struggle with different resolutions

@huraqan3761 3 ай бұрын

De-noised bread, got it!

@DeepakSingh-ji3zo 3 ай бұрын

This is just excellent!! Animations and Analogies were pure gold.

@Nazrininator 3 ай бұрын

I like how you added the Physics Simulation clip. I like it.

@lex_darlog_fun 3 ай бұрын

Diffusion transformers in general? Yes, please!

@TankorSmash 3 ай бұрын

That bread analogy was 100% chatgpt

@Words-. 3 ай бұрын

Thank you for finally explaining!

@TahuRock 3 ай бұрын

GOATED VIDEO 💪🏾💪🏾💪🏾

@Random_person_07 2 ай бұрын

You should make a video of how Ai TTS works and different types and stuff

@MilesBellas 3 ай бұрын

Baking Bread = great metaphor

@niklase5901 3 ай бұрын

You are my fav AI channel so it would be great to hear your take on Yann LeCun idea on how to build human level intelligence. He held a talk about this on the Hudson forum recently. Instead of LLM:s he wants to build models that truly models works by predicting the state of the world given some action. I can see how that would be a very effective model, but I suspect it will be easier to get around all the short falls of LLM, than to build this fancy model LeCun suggests. What do you think?

@dpactootle2522 3 ай бұрын

I watched half of the video to remind myself that life can suck a lot sometimes.

@snylekkie 3 ай бұрын

@bycloud do you know if anyone encoded math statements as integers like Gödel did, and used that as a custom LLM encoder for math proofs?

@TheDreamFx 3 ай бұрын

Hey! Great video! It would be nice if you cloud link your blog in the video description :)

@n45a_ 3 ай бұрын

wth i just thought that i need an explanation for diff transformers erlier today

@iknowsolittle 3 ай бұрын

How are you this smart and knowledgeable? Dont answer that. I just think ur super cool dude haha

@ulamss5 3 ай бұрын

at some point the bread analogy was harder to understand than the actual math

@7image 3 ай бұрын

3 views in 2 mins bro fell off🔥Shout out my favorite nigerian tech youtuber

@bycloudAI 3 ай бұрын

going for the "ranking by views: 10 of 10" for this one 🔥🔥🔥🗣️🗣️🗣️

@DynamicLights 3 ай бұрын

@@bycloudAIlol

@DynamicLights 3 ай бұрын

He is Nigerian how do u know?

@StefanReich 3 ай бұрын

Bro does NOT sound Nigerian

@7image 3 ай бұрын

@@DynamicLights I personally met him in abuja

@kingki1953 3 ай бұрын

In summary: put noise dough to oven and cook it to become AI video generator 🗿

@starbez 3 ай бұрын

Shouldn't sponsored content be mentioned within the first minute of a KZbin video?

@haukauntrie 3 ай бұрын

Why would it?

@EvaDawnley 3 ай бұрын

Does open sora have a huggingface?

@pedrogorilla483 3 ай бұрын

Just one day after you release this video we have Allegro, new open source video model. Check it out.

@LonewolfeSlayer 3 ай бұрын

Someone mentioned it but is the algorithm just messing with you at this point. You used to get a lot of views.

@mirek190 3 ай бұрын

so everting is transformants now ... interesting

@albert123a 3 ай бұрын

Just put the fries in the bag bro

@Eric-yd9dm 3 ай бұрын

> I am really good at having great timing - cloud,By on making videos about an area with research speed bonus modifiers correlated to the number of youtube videos about it =P

@LumiLumiLumiLumiLumiLumiLumiL 3 ай бұрын

Can u cover Neuro Sama? How she's made etc. how one could re-create her?

@raspberryjam 3 ай бұрын

Vedal isn't making that information public. Maybe one day, but for now it's under lock and key

@LumiLumiLumiLumiLumiLumiLumiL 3 ай бұрын

@@raspberryjam well its easy to Kind of guess! Its clearly a LLM and maybe some tts like sovits... The llm will prolly be something like Mistral as Qwen needs commercial and Llama the 'Built with Llama' etc. He said there is an LLM as a filter and a way for the Ai to feel emotions. He said something about watching movies and having feelings.