AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

Scaling Laws for Diffusion Transformers

Zhengyang Liang, Hao He, Ceyuan Yang, Bo Dai

ICLR 2026 · Image generation › Fast diffusion sampling · approach: Fast diffusion ODE solvers · 43 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 in-context conditioning with cross-attention conditioningDiT scaling law · Scaling exponents (loss vs compute)loss exponent: -0.0273 -> -0.0385Improved
replace in-context conditioning with cross-attention conditioningDiT scaling law · Scaling exponents (allocation)model exponent / data exponent: model 0.56 -> 0.54, data 0.43 -> 0.46Mixed
mix models of aspect ratio 32 and 64 instead of fixing ratio at 64 (ablation)isoFLOP model fitting · Loss vs parameters at fixed computetrend clarityHurt
evaluate scaling on out-of-domain COCO 2014 validation instead of in-domain dataDiT scaling law · COCO 2014 valvalidation loss, VLB, likelihood, FIDNo clear effect
extrapolate fitted law to 1.5e21 FLOPs with 958.3M-parameter modelDiT scaling law · Laion-Aesthetic subsettraining lossImproved

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