Oral Image Generations

Visual Autoregressive Modeling (VAR) revolutionizes image generation by using a coarse-to-fine ’next-scale prediction’, outperforming diffusion models and exhibiting scaling laws similar to LLMs.

Stylus: an automatic adapter selection system for diffusion models, boosts image quality and diversity by intelligently composing task-specific adapters based on prompt keywords.

Revolutionizing image generation, Representation-Conditioned Generation (RCG) achieves state-of-the-art results in unconditional image synthesis by leveraging self-supervised representations to condit…

DMD2 dramatically speeds up image generation by cleverly distilling expensive diffusion models, achieving state-of-the-art results without sacrificing quality.

Boost image quality in diffusion models without reducing variation using Autoguidance: guide a high-quality model with a less-trained version of itself!