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 | Projected GAN (DINOv2) | FD | 636.35 | — | Unverified |
| 2 | Diffusion ProjectedGAN (DINOv2) | FD | 547.61 | — | Unverified |
| 3 | Unleashing Transformers (DINOv2) | FD | 440.04 | — | Unverified |
| 4 | Consistency (DINOv2) | FD | 428.99 | — | Unverified |
| 5 | StyleGAN (DINOv2) | FD | 239.79 | — | Unverified |
| 6 | Denoising Diffusion Probabilistic Model (large, DINOv2) | FD | 229.76 | — | Unverified |
| 7 | iDDPM (DINOv2) | FD | 166.19 | — | Unverified |
| 8 | ADM (dropout, DINOv2) | FD | 59.64 | — | Unverified |
| 9 | VQGAN | FID-10k-training-steps | 59.63 | — | Unverified |
| 10 | StackGAN-v2 | FID | 35.61 | — | Unverified |