ImageNet-512x512 imagenet-512x512 Leaderboard
Auto-discovered from papers reporting ImageNet-512x512 (FID). · Metric: FID (lower is better)
| # | Model | FID | Paper |
|---|---|---|---|
| 1 | Unified Latents (UL): How to train your latents | 1.40 | — |
| 2 | PixelDiT: Pixel Diffusion Transformers for Image Generation | 1.81 | — |
| 3 | There is No VAE: End-to-End Pixel-Space Generative Modeling via Self-Supervised Pre-training | 2.35 | — |
| 4 | Terminal Velocity Matching | 4.32 | — |