AI Paper Atlas

Research map / Benchmarks / ImageNet 64×64

ImageNet 64×64 leaderboard

19 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on ImageNet 64×64. Best FID: 1.035 (EDM2-S + AutoG + REG, ICML 2025).

Numbers are as each paper reports them, read by AI from its results tables and not checked by hand. Papers can differ in setting (training data, model size, extra data); the topic column shows what each paper is about. Open the paper before you compare or quote a number.

ImageNet 64×64 · FID

19 papers, each with its best reported number for its own method; lower is better.

#FID ↓MethodPaperTopic
11.035EDM2-S + AutoG + REG
EDM2-S
REG: Rectified Gradient Guidance for Conditional Diffusion Models
ICML 2025 · Table: Class-conditional Image
Fast diffusion sampling
21.21PaGoDA
EDM
PaGoDA: Progressive Growing of a One-Step Generator from a Low-Resolution Diffusion Teacher
NeurIPS 2024 · Table: Experimental results of
Fast diffusion sampling
31.28DMD2 (longer training)
EDM
Improved Distribution Matching Distillation for Fast Image Synthesis
NeurIPS 2024 · Image quality comparison on Im
Fast diffusion sampling
41.38DisBack
EDM
Distribution Backtracking Builds A Faster Convergence Trajectory for Diffusion Distillation
ICLR 2025 · Table: conditional generation
Fast diffusion sampling
51.44Corrector optimizedScore-Optimal Diffusion Schedules
NeurIPS 2024 · Table 1
Fast diffusion sampling
61.46CoSIM, 4 NFE
VP-EDM score network
Continuous Semi-Implicit Models
ICML 2025 · Table: Conditional generation
Fast diffusion sampling
72.16LEGO-L-PGLearning Stackable and Skippable LEGO Bricks for Efficient, Reconfigurable, and Variable-Resolution Diffusion Modeling
ICLR 2024 · Table: FID results on ImageNet
Autoregressive and latent generation
82.18CCM
OT-CFM
See Further When Clear: Curriculum Consistency Model
CVPR 2025 · Table 1(b)
Fast diffusion sampling
92.21DiMR-L/3RAlleviating Distortion in Image Generation via Multi-Resolution Diffusion Models and Time-Dependent Layer Normalization
NeurIPS 2024 · Appendix, ImageNet 64×64 table
Autoregressive and latent generation
102.62DMD
EDM
One-step Diffusion with Distribution Matching Distillation
CVPR 2024 · Table 1
Fast diffusion sampling
9 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

Not affiliated with any conference, journal or the benchmark's authors. Corrections: contact@latenticlabs.com.