Hacker News with Generative AI: Diffusion Models

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 Without Tears (notion.site)
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.
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.
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.
Diffusion models are real-time game engines (gamengen.github.io)
DifuzCam: Replacing Camera Lens with a Mask and a Diffusion Model (arxiv.org)
Diffusion Training from Scratch on a Micro-Budget (arxiv.org)
Diffusion Texture Painting (nvidia.com)
CAT3D: Create Anything in 3D with Multi-View Diffusion Models (cat3d.github.io)