Ben Waber · @bwaber
691 followers · 2652 posts · Server hci.social

Next was an incredible talk by Yang Song on and score-based generative models at MIT Brain and Cognitive Sciences. This is hands down the most thorough talk I've heard on the ins and outs of how to implement generative models. Highly recommend youtube.com/watch?v=wMmqCMwuM2 (4/8)

#Diffusion #generativeAI #ai #LLMs

Last updated 1 year ago

hlfshell · @hlfshell
72 followers · 313 posts · Server hachyderm.io

Question for those of you attuned to this field - are GANs still utilized or have diffusion models largely replaced them? Not just in the image domain either, I'm talking about in general.

If GANs are still utilized in a particular field, then I ask - for what? What kinds of GANs?

#gan #Diffusion #deeplearning #machinelearning #ai

Last updated 1 year ago

Pistache · @11pistache
0 followers · 8 posts · Server piaille.fr
Francis Ho · @Sunfishstanford
786 followers · 252 posts · Server hachyderm.io

Here is a deeper dive on the relationship between filtrations and our information on stochastic processes:

freeenergy.blog/2023/Filtratio

#math #probability #Diffusion #stochastic

Last updated 1 year ago

Francis Ho · @Sunfishstanford
785 followers · 247 posts · Server hachyderm.io

I started to learn about stochastic calculus because many of the most interesting breakthroughs these days (e.g., diffusion probabilistic models for generative AI) involve stochastic processes. There are a lot of new and confusing concepts: Lebesgue integrals, measure theory, sigma algebras and Borel sets, martingales, rigorous probability theory, etc. Here is a post on a few learnings related to martingales:

freeenergy.blog/embracing%20tr

#math #probability #Diffusion

Last updated 1 year ago

· @mag
22 followers · 533 posts · Server piaille.fr

Bon, pendant que l'illuminé de l'Elysée pousse la chansonnette avec des fafs subventionnés par la DRAC (fatiiiigue), ça me rappelle qu'il faut que je vous dise qu'on cherche un.e chargé.e de production et de diffusion pour 2 compagnies de danse strasbourgoises et leurs spectacles de qualité (eux, na !) pour 20h/mois en CDDU. Réseaux (au pluriel😉) Jeune public, Rue, et hors les murs. Venez, on se met de côté et on en discute 😉
!

#quonseledise #recrutement #danse #Diffusion #production #partagez

Last updated 2 years ago

Francis Ho · @Sunfishstanford
754 followers · 205 posts · Server hachyderm.io

I'm trying to understand the Sohl-Dickstein 2015 paper (arxiv.org/pdf/1503.03585.pdf) on generative diffusion probabilistic models, and for the longest time was hung up on how the reverse process could work. Clearly, a reverse random walk is very unlikely to go back to the original spot. Then I realized that we just need to "fine-tune" the mean and stdev to make it go backwards. Here is a simple example that brute forces that: colab.research.google.com/driv

#generative #ml #Diffusion

Last updated 2 years ago

Ben Waber · @bwaber
508 followers · 1377 posts · Server hci.social

Next was a great talk by Greg Ver Steeg on the inner workings of models at the Information Sciences Institute. This talk provides solid theoretical groundwork for grasping this approach, highly recommend youtube.com/watch?v=8azWhUug7m (6/11)

#Diffusion #usc #ai

Last updated 2 years ago

Alex J. Champandard 🌱 · @alexjc
1611 followers · 1905 posts · Server creative.ai

This is acknowledgement that models extract the expression from input training data, store it (like a time-delayed photocopier) then output that expression on demand.

Since the prompt, by definiton, can't contain the expression, it must have come frm Copyrighted data.

#Diffusion

Last updated 2 years ago

Alex J. Champandard 🌱 · @alexjc
1607 followers · 1894 posts · Server creative.ai

There is no direct legal requirement for companies to respect opt-in, but indirectly, many customers have requirements for IP that definitely depend on opt-in!

The games industry is quickly revising its outsourcing contracts to ensure no infringing systems are used...

#Diffusion

Last updated 2 years ago

Alex J. Champandard ❄️ · @alexjc
1602 followers · 1840 posts · Server creative.ai

Adobe is distributing 248M stock images. I presume the total of public domain and creative commons images are less than that, so upper bound is 500M images for a model of that quality.

(Technical analysis only, no comment on legality or ethicalness.)

#Diffusion

Last updated 2 years ago

Alex J. Champandard ❄️ · @alexjc
1587 followers · 1705 posts · Server creative.ai

One reason -style models are here to stay, even if GANs make a come-back in quality: they are more flexible.

A model has an encoder and decoder, so you can feed in images and get useful stuff back out. In-Painting, Out-Painting, style transfer, blending...

#Diffusion

Last updated 2 years ago

Alex J. Champandard ❄️ · @alexjc
1585 followers · 1695 posts · Server creative.ai

When training models, you know how the loss value is significantly differently calibrated for different timesteps...

Does anyone normalize these? I've seen papers where they blur the image, I presume that helps calibrate the losses better?

#Diffusion

Last updated 2 years ago

無夢星球 · @dreamplan2501
147 followers · 4156 posts · Server mastodon.world

RT @kadirnar_ai
Prompt-to-Prompt Image Editing with Cross-Attention Control

Demo: huggingface.co/spaces/kadirnar

#huggingface #stableDifusion #paper #Diffusion

Last updated 2 years ago

AIME · @aime
16 followers · 21 posts · Server techhub.social

AudioLDM: Text-to-Audio Generation with Latent Diffusion Models, a TTA system that is built on a latent space to learn the continuous audio representations from contrastive language-audio pretraining (CLAP) latents.

audioldm.github.io

#deeplearning #Diffusion

Last updated 2 years ago

AIME · @aime
16 followers · 20 posts · Server techhub.social

Dreamix: Video Diffusion Models are General Video Editors

dreamix-video-editing.github.i

#deeplearning #Diffusion

Last updated 2 years ago

Ben Waber · @bwaber
423 followers · 725 posts · Server hci.social

First was an interesting talk by @danielromero on the influence of , identity, and on linguistic innovation at the . New terms seem to diffuse differently for urban and rural areas, and this work points out the need for models to incorporate socioeconomic factors youtube.com/watch?v=MSYlFl_V14 (2/6)

#networks #geography #Diffusion #nico

Last updated 2 years ago

Kenny Smith · @kennysmith
82 followers · 684 posts · Server mstdn.social

@benbloodworth I haven’t seen a move from my bunch after that first, small, wave came over. I just checked with one of those third-party apps and did a word search, too. I think some are sticking around there, or just went elsewhere.

This will make for an excellent of for someone’s dissertation. (If they could ever discover this post via the miserable .)

((In addition to your excellent list, I’m going to soon need a better app experience.))

#search #study #innovation #Diffusion

Last updated 2 years ago

Guido Schmidt · @guidoschmidt
476 followers · 389 posts · Server genart.social
Guido Schmidt · @guidoschmidt
476 followers · 388 posts · Server genart.social