Diffusion models have significantly advanced the fields of image, audio, and video generation, but they depend on an iterative sampling process that causes slow generation.
本文为英文原文，点击下方按钮一键翻译为中文。
相关推荐
13.5万星！最强本地AI绘画引擎ComfyUI深度解析
2026-10-01 14:03
FlashDiffusion: Fused Tiled Kernel Spectral Decomposition
2026-10-01 12:00
Scaling and Distilling Text Embeddings for Better Diffusibility
2026-10-01 11:59
GFD-OPD: Guidance-Folded On-Policy Distillation of Diffusion Models Across Scales
2026-09-30 21:16
Graph Residual Conjugate Diffusion: SNR-Equalized Heat Flow for Graph Signals
2026-09-30 20:58
From Modes to Memories: Characterizing the Scale-Space Dynamics of Diffusion Models
2026-09-30 20:52