| Paper | Code | FID | Clean-FID (trainfull) | ModelName | ReleaseDate |
|---|---|---|---|---|---|
| Ensembling Off-the-shelf Models for GAN Training | ✓ Link | 3.87 | 3.98 ± 0.03 | Vision-aided GAN | 2021-12-16 |
| Projected GANs Converge Faster | ✓ Link | 3.89 | Projected GAN | 2021-11-01 | |
| Diffusion Models Beat GANs on Image Synthesis | ✓ Link | 5.57 | ADM (dropout) | 2021-05-11 | |
| Polarity Sampling: Quality and Diversity Control of Pre-Trained Generative Networks via Singular Values | ✓ Link | 6.34 | Polarity-StyleGAN2 | 2022-03-03 | |
| Analyzing and Improving the Image Quality of StyleGAN | ✓ Link | 6.93 | 6.97 ± 0.16 | StyleGAN2 | 2019-12-03 |
| Denoising Diffusion Probabilistic Models | ✓ Link | 19.75 | Denoising Diffusion Probabilistic Model | 2020-06-19 | |
| Progressive Growing of GANs for Improved Quality, Stability, and Variation | ✓ Link | 37.52 | 38.35 ± 0.32 | PGGAN | 2017-10-27 |
| A Style-Based Generator Architecture for Generative Adversarial Networks | ✓ Link | 8.72 ± 0.03 | StyleGAN | 2018-12-12 |