Tuesday, September 26, 2023

Introducing DeciDiffusion 1.0: 3x the Speed of Stable Diffusion with the Same Quality

Impressive! Their blog post describes a novel, good, and clever combination of various very recent machine learning methods.

"Deci is thrilled to present DeciDiffusion 1.0, our cutting-edge text-to-image latent diffusion model, which we’re proudly sharing with the open-source community. With 1.02 billion parameters, DeciDiffusion outpaces the comparably-sized 1.07 billion parameter Stable Diffusion v1.5 and achieves equal quality in 40% fewer iterations. Combined with our Inference SDK, Infery, DeciDiffusion is 3x faster than Stable Diffusion v1.5, producing Stable Diffusion-caliber images in under a second on affordable NVIDIA A10G GPUs. This leap in performance is driven by DeciDiffusion’s innovative architecture and specialized training techniques optimized for top-tier inference quality. DeciDiffusion’s architecture was designed for optimal inference efficiency, leveraging the power of AutoNAC, Deci’s proprietary Neural Architecture Search engine. ..."

Introducing DeciDiffusion 1.0: 3x the Speed of Stable Diffusion with the Same Quality




No comments: