AI Paper Atlas

Research map / Benchmarks / ImageNet 256×256

ImageNet 256×256 leaderboard

50 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on ImageNet 256×256. Best FID: 1.35 (LightningDiT, CVPR 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 256×256 · FID

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

#FID ↓MethodPaperTopic
11.35LightningDiT
LightningDiT-XL
Reconstruction vs. Generation: Taming Optimization Dilemma in Latent Diffusion Models
CVPR 2025 · Table 3
Autoregressive and latent generation
21.46TexTok-256 + DiT-XL
DiT-XL
Language-Guided Image Tokenization for Generation
CVPR 2025 · Table 2(a)
Autoregressive and latent generation
31.56PaGoDA
EDM
PaGoDA: Progressive Growing of a One-Step Generator from a Low-Resolution Diffusion Teacher
NeurIPS 2024 · Table: Experimental results of
Fast diffusion sampling
41.57eMIGM-HEffective and Efficient Masked Image Generation Models
ICML 2025 · Table: Image generation result
Autoregressive and latent generation
51.58DiT-SADM
DiT
Structure-Guided Adversarial Training of Diffusion Models
CVPR 2024 · Table 1
GANs
61.73VAR-d30-reVisual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction
NeurIPS 2024 · Table (ImageNet 256×256 compar
Autoregressive and latent generation
71.75BFM-XL-SF
DiT-XL
Blockwise Flow Matching: Improving Flow Matching Models For Efficient High-Quality Generation
NeurIPS 2025 · System-level comparison table
Fast diffusion sampling
81.86DiT-XL/2 + Interval CFG + REG
DiT-XL/2
REG: Rectified Gradient Guidance for Conditional Diffusion Models
ICML 2025 · Table: Class-conditional Image
Fast diffusion sampling
91.95HMAR-d30HMAR: Efficient Hierarchical Masked Auto-Regressive Image Generation
CVPR 2025 · Table 1
Autoregressive and latent generation
101.96STEI + guidance interval
SiT-XL/2
Learning to Integrate Diffusion ODEs by Averaging the Derivatives
NeurIPS 2025 · Table: Class-conditional resul
Fast diffusion sampling
36 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

ImageNet 256×256 · IS

23 papers, each with its best reported number for its own method; higher is better.

#IS ↑MethodPaperTopic
1362IAR-XXL (CFG=2.5)
LlamaGen-XXL
Improving Autoregressive Visual Generation with Cluster-Oriented Token Prediction
CVPR 2025 · Table 1
Language, safety and interpretability
2350.2VAR-d30-reVisual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction
NeurIPS 2024 · Table (ImageNet 256×256 compar
Autoregressive and latent generation
3334.5HMAR-d30HMAR: Efficient Hierarchical Masked Auto-Regressive Image Generation
CVPR 2025 · Table 1
Autoregressive and latent generation
4332.42NFIG
VAR Transformer
NFIG: Multi-Scale Autoregressive Image Generation via Frequency Ordering
NeurIPS 2025 · Main results table
Autoregressive and latent generation
5318.64RaceDiT-XL/2-4in32
DiT-XL/2
Expert Race: A Flexible Routing Strategy for Scaling Diffusion Transformer with Mixture of Experts
ICML 2025 · Table: Comparison with other m
Mixture of experts
6317.77RandAR-XL (88 steps)
LLaMAGen-XL
RandAR: Decoder-only Autoregressive Visual Generation in Random Orders
CVPR 2025 · Table 1
Autoregressive and latent generation
7298.46DiT-SADM
DiT
Structure-Guided Adversarial Training of Diffusion Models
CVPR 2024 · Table 1
GANs
8289.4BFM-XL-SF
DiT-XL
Blockwise Flow Matching: Improving Flow Matching Models For Efficient High-Quality Generation
NeurIPS 2025 · System-level comparison table
Fast diffusion sampling
9284.31DyDiT-XL λ=0.7
DiT-XL
Dynamic Diffusion Transformer
ICLR 2025 · Table: Comparison with state-o
Fast diffusion sampling
10276.8LlamaGen-3B + CCA
LlamaGen-3B
Toward Guidance-Free AR Visual Generation via Condition Contrastive Alignment
ICLR 2025 · Table 1
Multimodal LLMs
13 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.