Image
104 resources · page 4 of 4
DDPM
by Jonathan Ho et al. (UC Berkeley)
arXiv paper (2020) "Denoising Diffusion Probabilistic Models", introducing DDPM image generation by learning to reverse a gradual noising process.
DiT (Scalable Diffusion Transformers)
by William Peebles and Saining Xie (UC Berkeley)
arXiv paper (2022) introducing Diffusion Transformers (DiT), scalable diffusion models with transformer backbones.
Flow Matching
by Yaron Lipman et al. (Meta AI)
arXiv paper (2022) "Flow Matching for Generative Modeling", introducing flow matching for training continuous normalising flows.
GANs (Goodfellow)
by Ian J. Goodfellow et al. (Université de Montréal)
arXiv paper (2014) by Goodfellow et al. introducing generative adversarial networks (GANs) and adversarial training.
Gemini image generation got it wrong (postmortem)
by Google
Google post explaining what went wrong with Gemini's image generation of people and the planned fixes.
Hi3D API introduction
Hi3D API introduction: image-to-3D generation API from Math Magic based on its Sparc3D and Ultra3D models.
Latent Diffusion (Stable Diffusion)
by Robin Rombach et al. (LMU Munich and Runway)
arXiv paper (2021) introducing latent diffusion models, the basis of Stable Diffusion.
VAE (Kingma & Welling)
by Diederik P Kingma and Max Welling (University of Amsterdam)
arXiv paper (2013) "Auto-Encoding Variational Bayes", introducing the variational autoencoder (VAE).