Class-conditional image generation on ImageNet-1k 512x512
1.66FIDRAR-XXL
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| RAR-XXLType=AR, Params=1.4B, Arbitrary Resolutions=✗, Tokens=10242026.04 | 1.66 | 295.7 | — | — | — | |
| MAGVIT-v2Type=Mask, Params=307M, Arbitrary Resolutions=✗, Tokens=10242026.04 | 1.91 | 324.3 | — | — | — | |
| TiTok-S/B-128Type=Mask, Params=287M, Arbitrary Resolutions=✗, Tokens=1282026.04 | 2.13 | — | — | — | — | |
| VAR-d30Type=VAR, Params=2B, Arbitrary Resolutions=✗, Tokens=22402026.04 | 2.63 | 303.2 | — | — | — | |
| VibeToken-Gen-XXLType=AR, Params=1.5B, Arbitrary Resolutions=✓, Tokens=642026.04 | 3.6 | 230.33 | — | — | — | |
| MaskGITType=Mask, Params=177M, Arbitrary Resolutions=✗, Tokens=10242026.04 | 4.46 | 342 | — | — | — | |
| VibeToken-Gen-BType=AR, Params=87M, Arbitrary Resolutions=✓, Tokens=642026.04 | 7.48 | 189.43 | — | — | — | |
| SSCModel=SiT-XL/2, Base Method=REPA2026.05 | 8.39 | — | 5.18 | 79 | 61 | |
| REPAModel=SiT-XL/22026.05 | 11.72 | — | 10.4 | 76 | 62 | |
| SSCModel=SiT-B/2, Base Method=REPA2026.05 | 25.15 | — | 6.32 | 71 | 63 | |
| REPAModel=SiT-B/22026.05 | 31.73 | — | 13.76 | 67 | 61 |