AI Paper Atlas

Research map / Benchmarks / FFHQ

FFHQ leaderboard

74 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on FFHQ. Best FID: 2.21 (LENeRF, CVPR 2023).

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 · FID

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

#FID ↓MethodPaperTopic
12.21LENeRF
EG3D
Local 3D Editing via 3D Distillation of CLIP Knowledge
CVPR 2023 · Table 1
NeRF and radiance fields
22.45Spider StyleGAN2-ADA (TinyImageNet input)
StyleGAN2-ADA
Spider GAN: Leveraging Friendly Neighbors To Accelerate GAN Training
CVPR 2023 · Table: FFHQ FID comparison
GANs
32.46Corrector optimizedScore-Optimal Diffusion Schedules
NeurIPS 2024 · Table 1
Fast diffusion sampling
42.67Simple ReFlow + GuidanceSimple ReFlow: Improved Techniques for Fast Flow Models
ICLR 2025 · Comparison of neural ODE metho
Fast diffusion sampling
52.67StyleGAN-V2 + MaEM-GAN
StyleGAN-V2
Combating Mode Collapse via Offline Manifold Entropy Estimation
AAAI 2023 · Table 7
Recognition and long-tail
62.8Ours
StyleGAN2
Domain Expansion of Image Generators
CVPR 2023 · Table 2
Autoregressive and latent generation
72.87MQGAN
VQGAN
Learning to Quantize for Training Vector-Quantized Networks
ICML 2025 · Table 5
Autoregressive and latent generation
82.9GLeaD + GGDR
StyleGAN2
GLeaD: Improving GANs With a Generator-Leading Task
CVPR 2023 · Table 1
GANs
92.91SpatialGAN
StyleGAN2
Spatial Steerability of GANs via Self-Supervision from Discriminator
TPAMI 2024 · Table 3
GANs
103.12Conditional StyleGAN2-ADA, FFHQ+EFHQ
StyleGAN2-ADA
EFHQ: Multi-purpose ExtremePose-Face-HQ dataset
CVPR 2024 · Table 2
Face and shape
64 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.