Hacker News with Generative AI: Diffusion Models

Gemini Diffusion (simonwillison.net)
Gemini Diffusion. Another of the announcements from Google I/O yesterday was Gemini Diffusion, Google's first LLM to use diffusion (similar to image models like Imagen and Stable Diffusion) in place of transformers.
Artificial Intelligence, Google, Diffusion Models, Generative AI
848 points by mdp2021 2 days ago | 230 comments
Gemini Diffusion (deepmind.google)
Generative AI, Diffusion Models, AI Art
61 points by og_kalu 3 days ago | 7 comments
Block Diffusion: Interpolating Autoregressive and Diffusion Language Models (m-arriola.com)
Diffusion language models offer unique benefits over autoregressive models due to their potential for parallelized generation and controllability, yet they lag in likelihood modeling and are limited to fixed-length generation. In this work, we introduce a class of block diffusion language models that interpolate between discrete denoising diffusion and autoregressive models.
Language Models, Diffusion Models, Machine Learning
72 points by t55 15 days ago | 16 comments
Watermark segmentation (github.com/Diffusion-Dynamics)
This repository by Diffusion Dynamics, showcases the core technology behind the watermark segmentation capabilities of our first product, clear.photo. This work leverages insights from research on diffusion models for image restoration tasks.
Image Processing, Computer Vision, Diffusion Models, Open Source
32 points by abriosi 39 days ago | 21 comments
Controlling Language and Diffusion Models by Transporting Activations (apple.com)
Large generative models are becoming increasingly capable and more widely deployed to power production applications, but getting these models to produce exactly what's desired can still be challenging.
Generative AI, Machine Learning, Artificial Intelligence, Language Models, Diffusion Models
90 points by 2bit 43 days ago | 15 comments
Lecture_diffusion_models.pdf (dropbox.com)
Machine Learning, Computer Science, PDF, Diffusion Models
5 points by Anon84 45 days ago | 3 comments
Simple Denoising Diffusion (github.com/utkuozbulak)
This repository contains a bare-bone implementation of denoising diffusion [1,2] in PyTorch, with majority of its code taken from The Annotated Diffusion and Phil Wang's diffusion repository.
Machine Learning, Diffusion Models, PyTorch, Open Source, Code
36 points by jvkersch 51 days ago | 0 comments
Why I find diffusion models interesting? (rnikhil.com)
I stumbled across this tweet a week or so back where this company called Inception Labs released a Diffusion LLM (dLLM). Instead of being autoregressive and predicting tokens left to right, here you start all at once and then gradually come up with sensible words simultaneously (start/finish/middle etc. all at once). Something which worked historically for image and video models is now outperforming similar-sized LLMs in code generation.
Generative AI, Machine Learning, Diffusion Models
202 points by whoami_nr 78 days ago | 86 comments
LLM generates the entire output at once (first diffusion LLM) [video] (youtube.com)
Generative AI, Diffusion Models, Artificial Intelligence, Video
4 points by amichail 78 days ago | 0 comments
First large diffusion-based LLM (twitter.com)
Something went wrong, but don’t fret — let’s give it another shot.
Generative AI, Diffusion Models
12 points by mjazwiecki 78 days ago | 1 comments
Large Language Diffusion Models (ml-gsai.github.io)
TL;DR: We introduce LLaDA, a diffusion model with an unprecedented 8B scale, trained entirely from scratch, rivaling LLaMA3 8B in performance.
Diffusion Models, Generative AI
45 points by SerCe 92 days ago | 12 comments
Diffusion Without Tears (notion.site)
Diffusion Models, AI, Generative AI, Computer Vision
62 points by jxmorris12 98 days ago | 20 comments
Stable Flow: Vital Layers for Training-Free Image Editing (omriavrahami.com)
Diffusion models have revolutionized the field of content synthesis and editing. Recent models have replaced the traditional UNet architecture with the Diffusion Transformer (DiT), and employed flow-matching for improved training and sampling. However, they exhibit limited generation diversity. In this work, we leverage this limitation to perform consistent image edits via selective injection of attention features.
Image Editing, Machine Learning, Computer Vision, Artificial Intelligence, Diffusion Models
12 points by gen-ai 115 days ago | 1 comments
Diffusion training from scratch on a micro-budget (github.com/SonyResearch)
This repository provides a minimalistic implementation of our approach to training large-scale diffusion models from scratch on an extremely low budget.
Machine Learning, Diffusion Models, Open Source, Budget Constraints, Research
135 points by lnyan 130 days ago | 23 comments
Pulsar: Secure Steganography for Diffusion Models (iacr.org)
Widespread efforts to subvert access to strong cryptography has renewed interest in steganography, the practice of embedding sensitive messages in mundane cover messages.
Cryptography, Steganography, Security, Artificial Intelligence, Diffusion Models
41 points by aliventer 244 days ago | 3 comments
Diffusion models are real-time game engines (gamengen.github.io)
Diffusion Models, Game Engines, Real-time, Artificial Intelligence
1149 points by jmorgan 268 days ago | 409 comments
DifuzCam: Replacing Camera Lens with a Mask and a Diffusion Model (arxiv.org)
Computer Vision, Machine Learning, Generative AI, Diffusion Models
116 points by dataminer 279 days ago | 47 comments
Diffusion Training from Scratch on a Micro-Budget (arxiv.org)
Diffusion Models, Machine Learning, Computer Vision, Budget
208 points by fzliu 297 days ago | 27 comments
Diffusion Texture Painting (nvidia.com)
Diffusion Models, Generative AI, Image Generation, Computer Graphics, NVIDIA
6 points by jhncls 307 days ago | 0 comments
CAT3D: Create Anything in 3D with Multi-View Diffusion Models (cat3d.github.io)
3D Modeling, AI, Generative AI, Diffusion Models
14 points by alphabetting 371 days ago | 2 comments