Image Generation
Image Generation (synthesis) is the task of generating new images from an existing dataset.
- Unconditional generation refers to generating samples unconditionally from the dataset, i.e. $p(y)$
- Conditional image generation (subtask) refers to generating samples conditionally from the dataset, based on a label, i.e. $p(y|x)$.
In this section, you can find state-of-the-art leaderboards for unconditional generation. For conditional generation, and other types of image generations, refer to the subtasks.
( Image credit: StyleGAN )
Papers
Showing 1–10 of 6689 papers
All datasetsImageNet 256x256CIFAR-10ImageNet 64x64ImageNet 512x512FFHQ 256 x 256CelebA 64x64ImageNet 32x32LSUN Bedroom 256 x 256STL-10LSUN Churches 256 x 256ImageNet 128x128FFHQ 1024 x 1024
Benchmark Results
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | ADM-G | FID | 7.72 | — | Unverified |
| 2 | MaskGIT | FID | 7.32 | — | Unverified |
| 3 | simple diffusion (U-ViT, L) | FID | 4.53 | — | Unverified |
| 4 | MaskGIT (a=0.05) | FID | 4.46 | — | Unverified |
| 5 | simple diffusion (U-Net) | FID | 4.28 | — | Unverified |
| 6 | ADM-G, ADM-U | FID | 3.85 | — | Unverified |
| 7 | Poly-INR | FID | 3.81 | — | Unverified |
| 8 | Latent Diffusion (LDM-4-G) | FID | 3.6 | — | Unverified |
| 9 | DPC-U | FID | 3.54 | — | Unverified |
| 10 | SiD-EDM2-XS (125M) | FID | 3.35 | — | Unverified |