AI Paper Atlas

Research map / Benchmarks / FFHQ-1024

FFHQ-1024 leaderboard

10 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on FFHQ-1024. Best FID: 3.01 (Ours (w/ ADA), CVPR 2022).

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.

FFHQ-1024 · FID

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

#FID ↓MethodPaperTopic
13.01Ours (w/ ADA)
StyleGAN2 (F)
Ensembling Off-the-Shelf Models for GAN Training
CVPR 2022 · Table: Results on full-dataset
GANs
23.326StyleGAN2, Spectral
StyleGAN2
Spectral Distribution Aware Image Generation
AAAI 2021 · Table 3
GANs
34.09CREPSEfficient Scale-Invariant Generator With Column-Row Entangled Pixel Synthesis
CVPR 2023 · Table: FID comparison
Autoregressive and latent generation
45.21TokenGANImproving Visual Quality of Image Synthesis by A Token-based Generator with Transformers
NeurIPS 2021 · Table 1
Editing and style transfer
55.23HDiT-85MScalable High-Resolution Pixel-Space Image Synthesis with Hourglass Diffusion Transformers
ICML 2024 · FFHQ comparison table
Autoregressive and latent generation
65.8Ours
StyleGAN2
Diversity-aware Channel Pruning for StyleGAN Compression
CVPR 2024 · Table 1
Fast diffusion sampling
78.1StyleNeRFStyleNeRF: A Style-based 3D Aware Generator for High-resolution Image Synthesis
ICLR 2022 · Appendix, Table 2
NeRF and radiance fields
810.13GIRAFFE HD
GIRAFFE
GIRAFFE HD: A High-Resolution 3D-Aware Generative Model
CVPR 2022 · Table: 512² and 1024² Resoluti
Editing and style transfer
912GRAM-HDGRAM-HD: 3D-Consistent Image Generation at High Resolution with Generative Radiance Manifolds
ICCV 2023 · Table 1
NeRF and radiance fields
1017.8MADFormer diffusion depth d=14
1.3B, 28 layers
$\textit{MADFormer}$: Mixed Autoregressive and Diffusion Transformers for Continuous Image Generation
ICLR 2026 · Diffusion depth table
Autoregressive and latent generation

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