shipfeedAI news, curated daily

00:34:33 CET
21 MAY00:34:33shipfeed
pull to refreshlast sync
Just in — 30 new
§ feed · storyline

Stable Diffusion 3.5 twice as fast with new TensorRT optimization

Stable Diffusion 3.5 receives TensorRT and FP8 optimization in collaboration with NVIDIA, doubling generation speed and lowering VRAM requirements on supported RTX GPUs.

Jun 12 · · primary fetch1 sourceupdated Jun 12 ·

In collaboration with NVIDIA, we've optimized the SD3.5 family of models using TensorRT and FP8, improving generation speed and reducing VRAM requirements on supported RTX GPUs.

read full article on stability.ai
§ sources1 publication · timeline below
  1. stability.aiStable Diffusion 3.5 Models Optimized with TensorRT Deliver 2X Faster Performance and 40% Less Memory on NVIDIA RTX GPUsprimary