AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

Improved Noise Schedule for Diffusion Training

Tiankai Hang, Shuyang Gu, Jianmin Bao, Fangyun Wei, Dong Chen, Xin Geng, Baining Guo

ICCV 2025 · Image generation › Fast diffusion sampling · approach: Denoising diffusion probabilistic models · 42 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace cosine schedule with Laplace noise scheduleDiT · ImageNet-256 (CFG=3.0)FID-10K: 11.06 -> 7.96Improved
replace cosine with Laplace schedule for each prediction targetDiT · ImageNet-256 (500K iters)FID-10K: 11.16 -> 8.48 (x0), 11.06 -> 7.96 (v), 10.46 -> 9.53 (epsilon)Improved
replace cosine with Laplace schedule at 512 resolutionDiT · ImageNet-512FID-10K: 11.91 -> 9.09Improved
replace cosine with Laplace schedule on unconditional facesDiT · CelebA 64x64FID: 7.93795 -> 6.58359Improved
replace cosine with Laplace schedule for text-to-imageDiT-base · CC12MFID: 58.3619 -> 54.3492Improved
change noise schedule instead of loss weighting (Min-SNR, Soft-Min-SNR) (ablation)DiT · ImageNet-256 (CFG=2.0)FID-10K: 9.07 -> 7.98Improved
use cosine-ply importance sampling as a loss weight instead of schedule (ablation)DiT · ImageNet-256 (CFG=2.0)FID-10K: 7.98 -> 8.88Hurt
shift the cosine schedule by mu=1 (ablation)Cosine schedule · ImageNet-256FID-10K: 10.85 -> 11.67 (CFG=2.0)Hurt
shift the cosine schedule by mu=-1 (ablation)Cosine schedule · ImageNet-256FID-10K: 10.85 -> 11.48 (CFG=2.0)Hurt
scale cosine schedule with 1/s=0.5 to concentrate near log SNR 0 (ablation)Cosine schedule · ImageNet-256 (CFG=2.0)FID-10K: 10.85 -> 8.04Improved
reduce 1/s from 0.5 to 0.25 in cosine scaled (ablation)Cosine Scaled · ImageNet-256FID-10K: 12.74 -> 15.83 (CFG=1.5), 11.02 -> 8.26 (CFG=3.0)Mixed
move Cauchy location mu from 0 to -1 or 1 (gamma=1) (ablation)Cauchy schedule · ImageNet-256 (CFG=2.0)FID-10K: 8.93 -> 10.38 (mu=-1), 10.19 (mu=1)Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy