Seonglae ChoGoogle Diffusion
playground
deepmind.google.com
https://deepmind.google.com/frontiers/gemini-diffusion
Gemini Diffusion
Gemini Diffusion is our state-of-the-art research model exploring what diffusion means for language – and text generation.
https://deepmind.google/models/gemini-diffusion/
Gemini Diffusion is our new experimental research model.
We’re always working on new approaches to improve our models, including making them more efficient and performant. Our latest research model, Gemini Diffusion, is a stat…
https://blog.google/technology/google-deepmind/gemini-diffusion/
DiffusionGemma
Good for local / low-concurrency inference, but offers limited cost advantage in large-scale cloud batch deployments. Quality is lower than standard Gemma 4.
DiffusionGemma: 4x faster text generation
An overview of DiffusionGemma, an exceptionally fast text generation model with up to 4x faster speeds.
https://blog.google/innovation-and-ai/technology/developers-tools/diffusion-gemma-faster-text-generation/
DiffusionGemma Technical Report
We introduce DiffusionGemma, an experimental open-weight language model that uses discrete diffusion to generate text at exceptionally high speed. Rather than decoding one token at a time,...
https://arxiv.org/abs/2608.00146
