Загрузка видео...

Не удалось загрузить видео

На главную

Results from a failed attempt to train a latent diffusion model on the results of my gabor image fitting process. The model doesn't do what it was supposed to, but I don't really mind what it's doing.

pixlpa's profile picture

Andrew 😵‍💫

10,919 subscribers

58,435 просмотров • 4 месяцев назад •via X (Twitter)

ИскусствоНаука и технологии
LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

This is a new diffusion-based language model from Inception. I don't know how well it works compared to an autoregressive LM of a similar size, but the inference process looks badass:
0:29

This is a new diffusion-based language model from Inception. I don't know how well it works compared to an autoregressive LM of a similar size, but the inference process looks badass:

BURKOV

58,434 просмотров • 1 год назад

Thanks to the Latent Consistency Model (LCM), we're nearing real-time image diffusion. I've made a simple MJPEG server for generation stream using diffusers img2img pipeline. It's really fun to play with it. Can't wait for the ControlNet version. try it:
0:37

Thanks to the Latent Consistency Model (LCM), we're nearing real-time image diffusion. I've made a simple MJPEG server for generation stream using diffusers img2img pipeline. It's really fun to play with it. Can't wait for the ControlNet version. try it:

Radamés Ajna

231,920 просмотров • 2 лет назад

First time i show a model like this Tenna 3D Model made for Jakeneutron 🔜 MAGfest2026 i had so much fun doing this model and i am super happy with the results, it was rushed but i did my best to work just fine for the animators!
1:25

First time i show a model like this Tenna 3D Model made for Jakeneutron 🔜 MAGfest2026 i had so much fun doing this model and i am super happy with the results, it was rushed but i did my best to work just fine for the animators!

Lukasz 🇧🇷

205,009 просмотров • 11 месяцев назад

"We live in a result oriented world. Everything is about results and very little is about the process. But, everything we do is about the process of what it takes to get the results. You've got to have a team full of champions before you're ever going to win a championship."
0:30

"We live in a result oriented world. Everything is about results and very little is about the process. But, everything we do is about the process of what it takes to get the results. You've got to have a team full of champions before you're ever going to win a championship."

The Winning Difference

362,760 просмотров • 2 лет назад

Gabor diffusion model attempt #2 - still decidely not making "images" but groovy in a way. Maybe if you squint your eyes? BTW, the motion here is just interpolation between random seeds but it's kind of a vibe.
1:40

Gabor diffusion model attempt #2 - still decidely not making "images" but groovy in a way. Maybe if you squint your eyes? BTW, the motion here is just interpolation between random seeds but it's kind of a vibe.

Andrew 😵‍💫

12,822 просмотров • 4 месяцев назад

I got a diffusion model to run really fast, glued it to a LLM, and it blows my mind how much of the interactivity we expect from software (editing text, dragging things around, clicking on "links") just works™️ in pixel space. The future of software is bright
0:41

I got a diffusion model to run really fast, glued it to a LLM, and it blows my mind how much of the interactivity we expect from software (editing text, dragging things around, clicking on "links") just works™️ in pixel space. The future of software is bright

Zain Shah

22,649 просмотров • 2 месяцев назад

AOC: That screenshot of what appeared to be a text message was a fabricated image. It was a fabricated image, I don't know where it came from, I don't know if it was staff of the committee,
1:30

AOC: That screenshot of what appeared to be a text message was a fabricated image. It was a fabricated image, I don't know where it came from, I don't know if it was staff of the committee,

Acyn

5,768,685 просмотров • 3 лет назад

Does that look weird to you (your race doesn't matter). It's Great Britain News. It's akin to having a White woman from Iceland doing the news in the heart of Haiti. It's a sloppy attempt at what? That I don't know, it's just wrong, it's difficult to watch.
0:20

Does that look weird to you (your race doesn't matter). It's Great Britain News. It's akin to having a White woman from Iceland doing the news in the heart of Haiti. It's a sloppy attempt at what? That I don't know, it's just wrong, it's difficult to watch.

Dane

50,290 просмотров • 10 месяцев назад

I notice that Sue O'Connell: COMMENTATOR, not a reporter was quick to assess the ethics of Turtleboy's conduct while still labeling it some form of "journalism" that "got results". What results did he get with this behavior, Sue? I know you were quick to opine on Karen Read's percieved "innocence" soley based on the defendant's word and little else. So, what conclusion do you draw from this defendant's words? Is this really ethical, or legal? So, please, tell me what "results" you think this conduct yielded? What do you think was intended?
11:31

I notice that Sue O'Connell: COMMENTATOR, not a reporter was quick to assess the ethics of Turtleboy's conduct while still labeling it some form of "journalism" that "got results". What results did he get with this behavior, Sue? I know you were quick to opine on Karen Read's percieved "innocence" soley based on the defendant's word and little else. So, what conclusion do you draw from this defendant's words? Is this really ethical, or legal? So, please, tell me what "results" you think this conduct yielded? What do you think was intended?

Masshole Mafia

21,616 просмотров • 7 месяцев назад

Meme Contest Results It's time to announce the winners of the contest: Thank you all for participating — it was truly a blast! What do you think of the entries?
0:29

Meme Contest Results It's time to announce the winners of the contest: Thank you all for participating — it was truly a blast! What do you think of the entries?

Zoo

22,689 просмотров • 1 год назад

This is the craziest model you'll see this week! This model powers Figma. It's also behind Wayfair and a bunch of major e-commerce retailers. This model is a PIXEL-PERFECT image editing model. Literally, "pixel perfect". The model is capable of modifying one image while keeping everything else untouched. It's a model designed, developed, and deployed by the research team at Jasper. This beats OpenAI models, Nano Banana, and every single general image model I've seen so far. It's up to 100x less expensive to run, and up to 10X faster. I recorded a quick video to show you how impressive this is. There's a ton of research behind this model. I'm adding two links below so you can read about how this model works, specifically about "Latent Bridge Matching" and "Flash Diffusion".
4:29

This is the craziest model you'll see this week! This model powers Figma. It's also behind Wayfair and a bunch of major e-commerce retailers. This model is a PIXEL-PERFECT image editing model. Literally, "pixel perfect". The model is capable of modifying one image while keeping everything else untouched. It's a model designed, developed, and deployed by the research team at Jasper. This beats OpenAI models, Nano Banana, and every single general image model I've seen so far. It's up to 100x less expensive to run, and up to 10X faster. I recorded a quick video to show you how impressive this is. There's a ton of research behind this model. I'm adding two links below so you can read about how this model works, specifically about "Latent Bridge Matching" and "Flash Diffusion".

Santiago

25,861 просмотров • 10 месяцев назад

Your AI sucks. And it's not the model. It's you. "Make it better" isn't a prompt, it's a guessing game. I changed one step in my process and the output quality completely flipped. Same ideas, same models, totally different results.
0:42

Your AI sucks. And it's not the model. It's you. "Make it better" isn't a prompt, it's a guessing game. I changed one step in my process and the output quality completely flipped. Same ideas, same models, totally different results.

Flick

322,001 просмотров • 1 месяц назад

The latent-vs-pixel debate misses the point. GPT Image 2 shows what users notice: pixel-level fidelity. Latent models show what scales: compact semantic structure. We connect them by replacing VAE/RAE decoders with a Pixel Diffusion Decoder. Code and Model available: 🧵(1/N)
0:48

The latent-vs-pixel debate misses the point. GPT Image 2 shows what users notice: pixel-level fidelity. Latent models show what scales: compact semantic structure. We connect them by replacing VAE/RAE decoders with a Pixel Diffusion Decoder. Code and Model available: 🧵(1/N)

Xuanchi Ren

669,581 просмотров • 3 месяцев назад

Eh, i'm really not impressed by GPT 5.6 sol lol. Asked it to recreate a 3 screen app design with image generation skill. Given how well it performs on benchmarks, I expected a lot more but the results were pretty ehhh. Not even close. Maybe I need to try harder but then... wasn't it supposed to do better?
0:36

Eh, i'm really not impressed by GPT 5.6 sol lol. Asked it to recreate a 3 screen app design with image generation skill. Given how well it performs on benchmarks, I expected a lot more but the results were pretty ehhh. Not even close. Maybe I need to try harder but then... wasn't it supposed to do better?

The Bugged Dev

154,059 просмотров • 2 месяцев назад

You imagine it. We create it. 🎨 Introducing #PixelStudio, a first-of-its-kind image generator on #Pixel9 powered by an on-device diffusion model¹ running on Tensor G4 and our Imagen 3 text-to-image model in the cloud.
0:34

You imagine it. We create it. 🎨 Introducing #PixelStudio, a first-of-its-kind image generator on #Pixel9 powered by an on-device diffusion model¹ running on Tensor G4 and our Imagen 3 text-to-image model in the cloud.

Made by Google

28,283 просмотров • 2 лет назад

I haven't finished my toga model yet, but these are the results. I learned to do better phys bones on the skirt, chest, bangs and more #himikotoga #3d #mha
1:03

I haven't finished my toga model yet, but these are the results. I learned to do better phys bones on the skirt, chest, bangs and more #himikotoga #3d #mha

Yumily (Commission OPEN 6/6)

18,853 просмотров • 2 месяцев назад

When u use Fable / Opus to generate models it can be quiet a pain in the ass to do small iterations. I also needed a way for the model to easily visualise the results of what he built so he could iterate over it. So I built a custom model viewer it can access and where I can easily fine tune models manually if needed. Used it for my game Valoria
2:26

When u use Fable / Opus to generate models it can be quiet a pain in the ass to do small iterations. I also needed a way for the model to easily visualise the results of what he built so he could iterate over it. So I built a custom model viewer it can access and where I can easily fine tune models manually if needed. Used it for my game Valoria

moht

11,198 просмотров • 2 месяцев назад

"What's he supposed to do? What is he supposed to do there?" "I really don't know. I think it's ridiculous." "It is ridiculous. It's football. It's absurd." Sean McDonough and Greg McElroy after a roughing the passer penalty negates a turnover for Notre Dame against Navy.
1:46

"What's he supposed to do? What is he supposed to do there?" "I really don't know. I think it's ridiculous." "It is ridiculous. It's football. It's absurd." Sean McDonough and Greg McElroy after a roughing the passer penalty negates a turnover for Notre Dame against Navy.

Awful Announcing

339,122 просмотров • 1 год назад

Tesla really goes out of their way to prevent anyone from hearing this. I think it sounds pretty cool! What do you think? This isn’t even a fancy model. Mid tier model Y, with a 4sec 0-60. I was doing some work on the car. Didn’t finish putting everything back, but had to drive it. Was surprised by how much more I could hear the motor noise. The camera is pointed at the missing rear seats, and the rear wheel motor is right under it.
1:19

Tesla really goes out of their way to prevent anyone from hearing this. I think it sounds pretty cool! What do you think? This isn’t even a fancy model. Mid tier model Y, with a 4sec 0-60. I was doing some work on the car. Didn’t finish putting everything back, but had to drive it. Was surprised by how much more I could hear the motor noise. The camera is pointed at the missing rear seats, and the rear wheel motor is right under it.

MG

33,022 просмотров • 6 месяцев назад