SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2403.08381 · CVPR · 2024

Tackling the Singularities at the Endpoints of Time Intervals in Diffusion Models

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

sian characteristics at singularity time steps. Based on this theoretical insight, we confirm the singularity at t = 1 is conditionally removable while it at t = 0 is an inherent property. Upon these significant conclusions, we propose a novel plug-and-play method SingDiffusion to address the initial singular time step sampling, which not only effectively resolves the average brightness issue for a wide range of diffusion models without extra training efforts, but also enhances their generation capability in achieving notable lower FID scores.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2403.08381")
get_code_for_paper("2403.08381")
have("2403.08381")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2403.08381.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2403.08381.svg)](https://syntology.ai/paper/2403.08381)

Connect an agent — have() is free.