OpenCodePapers

image-generation-on-ffhq-1024-x-1024

Image Generation
Dataset Link
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
Click a sortable column header to sort.
PaperCodeFIDbits/dimensionModelNameReleaseDate
SAN: Inducing Metrizability of GAN with Discriminative Normalized Linear Layer✓ Link1.61StyleSAN-XL2023-01-30
StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasets✓ Link2.02StyleGAN-XL2022-02-01
Polarity Sampling: Quality and Diversity Control of Pre-Trained Generative Networks via Singular Values✓ Link2.57Polarity-StyleGAN22022-03-03
MaGNET: Uniform Sampling from Deep Generative Network Manifolds Without Retraining✓ Link2.66MaGNET-StyleGAN22021-10-15
Alias-Free Generative Adversarial Networks✓ Link2.79StyleGAN3-T2021-06-23
Diffusion-GAN: Training GANs with Diffusion✓ Link2.83Diffusion StyleGAN22022-06-05
Analyzing and Improving the Image Quality of StyleGAN✓ Link2.84StyleGAN22019-12-03
Alias-Free Generative Adversarial Networks✓ Link3.07StyleGAN3-R2021-06-23
Feature Quantization Improves GAN Training✓ Link3.19FQ-GAN2020-04-05
Training Generative Adversarial Networks with Limited Data✓ Link3.62StyleGAN2 ADA+bCR2020-06-11
SWAGAN: A Style-based Wavelet-driven Generative Model✓ Link4.06SWAGAN-Bi2021-02-11
StyleNAT: Giving Each Head a New Perspective✓ Link4.17StyleNAT2022-11-10
A Style-Based Generator Architecture for Generative Adversarial Networks✓ Link4.4StyleGAN2018-12-12
StyleSwin: Transformer-based GAN for High-resolution Image Generation✓ Link5.07StyleSwin2021-12-20
MSG-GAN: Multi-Scale Gradients for Generative Adversarial Networks✓ Link5.8MSG-StyleGAN2019-03-14
Improved Transformer for High-Resolution GANs✓ Link6.37HiT-B2021-06-14
Image Generators with Conditionally-Independent Pixel Synthesis✓ Link10.07CIPS2020-11-27
Adversarial Latent Autoencoders✓ Link13.09StyleALAE2020-04-09
Efficient-VDVAE: Less is more✓ Link2.30Efficient-VDVAE2022-03-25
Very Deep VAEs Generalize Autoregressive Models and Can Outperform Them on Images✓ Link2.42Very Deep VAE2020-11-20
Check out how to contribute new results.