Google's DiffusionGemma generates 256 tokens in parallel and self-corrects as it goes

Google's open-source diffusion language model generates 256 tokens in parallel and self-corrects, hitting 4x speed on one GPU ...
VentureBeat

NYU’s new AI architecture makes high-quality image generation faster and cheaper

Researchers at New York University have developed a new architecture for diffusion models that improves the semantic representation of the images they generate. “Diffusion Transformer with ...

Google DeepMind releases DiffusionGemma, a model that runs local AI 4x faster

Most AI models are designed to be autoregressive—they generate text left to right one token at a time. DiffusionGemma has ...
TechCrunch

Stability claims its newest Stable Diffusion models generate more ‘diverse’ images

Following a string of controversies stemming from technical hiccups and licensing changes, AI startup Stability AI has announced its latest family of image-generation models. The new Stable Diffusion ...

Google open-sources speedy DiffusionGemma text diffusion model

Google says that DiffusionGemma can generate more than 1,000 tokens per second when running on a single H100, a server-grade ...
CNET

Stability AI Review: Stable Diffusion Is a Household Name in AI Images for a Reason

Our expert, award-winning staff selects the products we cover and rigorously researches and tests our top picks. If you buy through our links, we may get a commission. Katelyn is a reporter with CNET ...