Stanford's SPEED diffusion sampler accepted at NeurIPS, ~2X speedup training-free
hsu_byron · x · 2026-10-06
Stanford's Spectral Progressive Diffusion (SPEED) is accepted to NeurIPS 2026. The training-free progressive-resolution sampler speeds up image/video diffusion by 2X and stacks with distillation and feature caching like TeaCache. Code is open-sourced with ComfyUI and SGLang integrations.
More from Multimodal
- Dev uses GitHub Copilot app to generate a rebuildable 60s hype video via PR — DanWahlin · 2026-10-06
- Tencent releases new open-weight video generation model — Famous-Sport7862 · 2026-10-06
- Nano Banana 2.1 on Google Flow stuns with editorial portrait quality — full prompt shared — aziz4ai · 2026-10-06
- TagScribeR rebuilt: free local dataset studio with native LoRA training on AMD ROCm and NVIDIA — ArchAngelAries · 2026-10-06
- ComfyUI queue stuck? A maintainer's checklist to separate validation, node failures and lost progress — fluxdraw · 2026-10-06
- First try with Seedance 2.5: the model butchered the on-screen text at the end — atomantsmasher · 2026-10-06