Metric: rFID (lower is better)
| # | Model↕ | rFID▲ | Extra Data | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | SD-VAE (16x16) | 1.07 | No | High-Resolution Image Synthesis with Latent Diff... | 2021-12-20 | Code |
| 2 | MGVQ (16x16x4) | 1.59 | No | MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tok... | 2025-07-10 | Code |
| 3 | Open-Magvit2 (16x16) | 4.18 | No | Open-MAGVIT2: An Open-Source Project Toward Demo... | 2024-09-06 | Code |
| 4 | LlamaGen (16x16) | 5.59 | No | Autoregressive Model Beats Diffusion: Llama for ... | 2024-06-10 | Code |
| 5 | VQGAN (16x16) | 5.95 | No | Taming Transformers for High-Resolution Image Sy... | 2020-12-17 | Code |
| 6 | VAR (16x16) | 9.85 | No | Visual Autoregressive Modeling: Scalable Image G... | 2024-04-03 | Code |