TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

SotA/Medical/Image Generation/ImageNet 512x512

Image Generation on ImageNet 512x512

Metric: FID (lower is better)

LeaderboardDataset
Loading chart...

Results

Submit a result
#Model↕FID▲Extra DataPaperDate↕Code
1EDM2-L + DDO (SD-VAE, 25 steps, DPM-Solver-v3)1.21NoDirect Discriminative Optimization: Your Likelih...2025-03-03Code
2DDT-XL/2 + UCGM-S (SD-VAE + 150 sampling steps + CFG)1.24NoUnified Continuous Generative Models2025-05-12Code
3DDT-XL/2 + UCGM-S (SD-VAE + 100 sampling steps + CFG)1.25NoUnified Continuous Generative Models2025-05-12Code
4EDM2-XXL Autoguidance1.25NoGuiding a Diffusion Model with a Bad Version of ...2024-06-04Code
5DDT-XL/2(22en6de 675M + guidance interval )1.28NoDDT: Decoupled Diffusion Transformer2025-04-08Code
6EDM2- S Autoguidance (XS, T /16)1.34NoGuiding a Diffusion Model with a Bad Version of ...2024-06-04Code
7SiDA-EDM2-XXL (1.5B)1.366NoAdversarial Score identity Distillation: Rapidly...2024-10-19Code
8SiDA-EDM2-XL (1.1B)1.379NoAdversarial Score identity Distillation: Rapidly...2024-10-19Code
9EDM2-XXL w/ guidance interval1.4NoApplying Guidance in a Limited Interval Improves...2024-04-11Code
10SiDA-EDM2-L (777M)1.413NoAdversarial Score identity Distillation: Rapidly...2024-10-19Code
11SiD21.48NoSimpler Diffusion (SiD2): 1.5 FID on ImageNet512...2024-10-25-
12SiDA-EDM2-M (498M)1.488NoAdversarial Score identity Distillation: Rapidly...2024-10-19Code
13SiDA-EDM2-S (280M)1.669NoAdversarial Score identity Distillation: Rapidly...2024-10-19Code
14EDM2-S w/ guidance interval1.68NoApplying Guidance in a Limited Interval Improves...2024-04-11Code
15GMem1.71NoGenerative Modeling with Explicit Memory2024-12-11Code
16DC-AE-f32 + USiT-2B1.72NoDeep Compression Autoencoder for Efficient High-...2024-10-14Code
17MAR-L, Diff Loss1.73NoAutoregressive Image Generation without Vector Q...2024-06-17Code
18SIMS1.73NoSelf-Improving Diffusion Models with Synthetic D...2024-08-29-
19PaGoDA1.8NoPaGoDA: Progressive Growing of a One-Step Genera...2024-05-23Code
20EDM2-XXL1.81NoAnalyzing and Improving the Training Dynamics of...2023-12-05Code
21EDM2-XL1.85NoAnalyzing and Improving the Training Dynamics of...2023-12-05Code
22EDM2-L1.88NoAnalyzing and Improving the Training Dynamics of...2023-12-05Code
23SiD-EDM2-XL (1.1B)1.888NoAdversarial Score identity Distillation: Rapidly...2024-10-19Code
24SiD-EDM2-L (777M)1.907NoAdversarial Score identity Distillation: Rapidly...2024-10-19Code
25MAGVIT-v21.91NoLanguage Model Beats Diffusion -- Tokenizer is K...2023-10-09Code
26SiD-EDM2-XXL (1.5B)1.969NoAdversarial Score identity Distillation: Rapidly...2024-10-19Code
27EDM2-M2.01NoAnalyzing and Improving the Training Dynamics of...2023-12-05Code
28SiD-EDM2-M (498M)2.06NoAdversarial Score identity Distillation: Rapidly...2024-10-19Code
29TiTok-B-1282.13NoAn Image is Worth 32 Tokens for Reconstruction a...2024-06-11Code
30SiDA-EDM2-XS (125M)2.156NoAdversarial Score identity Distillation: Rapidly...2024-10-19Code
31EDM2-S2.23NoAnalyzing and Improving the Training Dynamics of...2023-12-05Code
32DiT-XL/2 with CADS2.31NoCADS: Unleashing the Diversity of Diffusion Mode...2023-10-26-
33StyleGAN-XL2.4NoStyleGAN-XL: Scaling StyleGAN to Large Diverse D...2022-02-01Code
34TiTok-L-642.49NoAn Image is Worth 32 Tokens for Reconstruction a...2024-06-11Code
35DiffiT2.67NoDiffiT: Diffusion Vision Transformers for Image ...2023-12-04Code
36SiD-EDM2-S (280M)2.707NoAdversarial Score identity Distillation: Rapidly...2024-10-19Code
37DiT-XL/2 with SA-Solver2.8NoSA-Solver: Stochastic Adams Solver for Fast Samp...2023-09-10Code
38DiMR-XL/3R2.89NoAlleviating Distortion in Image Generation via M...2024-06-13Code
39EDM2-XS2.91NoAnalyzing and Improving the Training Dynamics of...2023-12-05Code
40GIVT-Causal-L+A2.92NoGIVT: Generative Infinite-Vocabulary Transformers2023-12-04Code
41DiT-XL/23.04NoScalable Diffusion Models with Transformers2022-12-19Code
42MAGVIT-v2 (w/o guidance)3.07NoLanguage Model Beats Diffusion -- Tokenizer is K...2023-10-09Code
43SiD-EDM2-XS (125M)3.353NoAdversarial Score identity Distillation: Rapidly...2024-10-19Code
44DPC-U3.54No---
45Latent Diffusion (LDM-4-G)3.6NoHigh-Resolution Image Synthesis with Latent Diff...2021-12-20Code
46Poly-INR3.81NoPolynomial Implicit Neural Representations For L...2023-03-20Code
47ADM-G, ADM-U3.85NoDiffusion Models Beat GANs on Image Synthesis2021-05-11Code
48simple diffusion (U-Net)4.28NoSimple diffusion: End-to-end diffusion for high ...2023-01-26Code
49MaskGIT (a=0.05)4.46NoMaskGIT: Masked Generative Image Transformer2022-02-08Code
50simple diffusion (U-ViT, L)4.53NoSimple diffusion: End-to-end diffusion for high ...2023-01-26Code
51MaskGIT7.32NoMaskGIT: Masked Generative Image Transformer2022-02-08Code
52ADM-G7.72NoDiffusion Models Beat GANs on Image Synthesis2021-05-11Code