Generative Modeling on ImageNet (train)
1.19Fréchet Distance (FD)DRL (λ*)
Evaluation results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| DRL (λ*)Model=RAE, Embedder=Incep., λ=1, R1=10−5, cfg=2.25, interval=[.1, 1]2026.06 | 1.19 | — | — | — | — | |
| BaseModel=REPA, Embedder=Incep., λ=−−, R1=−−, cfg=2.25, interval=[.3, 1]2026.06 | 1.21 | — | — | — | — | |
| DRL (λ=1, R1=0)Model=RAE, Embedder=Incep., λ=1, R1=0, cfg=2.5, interval=[.1, 1]2026.06 | 1.25 | — | — | — | — | |
| BaseModel=RAE, Embedder=Incep., λ=−−, R1=−−, cfg=2, interval=[.1, 1]2026.06 | 1.28 | — | — | — | — | |
| BaseModel=SiT, Embedder=Incep., λ=−−, R1=−−, cfg=2, interval=[.3, 1]2026.06 | 1.5 | — | — | — | — | |
| DRL (λ*)Model=REPA, Embedder=Incep., λ=1, R1=10−5, cfg=1.5, interval=[.3, 1]2026.06 | 1.5 | — | — | — | — | |
| DRL (λ*)Model=SiT, Embedder=Incep., λ=1, R1=10−5, cfg=1.5, interval=[.3, 1]2026.06 | 1.78 | — | — | — | — | |
| DRL (λ=1, R1=0)Model=JiT, Embedder=Incep., λ=1, R1=0, cfg=2.5, interval=[.3, 1]2026.06 | 1.87 | — | — | — | — | |
| DRL (λ*)Model=JiT, Embedder=Incep., λ=1, R1=0, cfg=2.5, interval=[.3, 1]2026.06 | 1.87 | — | — | — | — | |
| BaseModel=JiT, Embedder=Incep., λ=−−, R1=−−, cfg=2.25, interval=[.1, 1]2026.06 | 1.91 | — | — | — | — | |
| DRL (λ=1, R1=0)Model=REPA, Embedder=Incep., λ=1, R1=0, cfg=1, interval=[0, 1]2026.06 | 2.14 | — | — | — | — | |
| DRL (λ=1, R1=0)Model=SiT, Embedder=Incep., λ=1, R1=0, cfg=1.25, interval=[.3, 1]2026.06 | 2.43 | — | — | — | — | |
| DRL (λ*)Model=RAE, Embedder=DINOv3-L, λ=5, R1=10−5, cfg=1.25, interval=[0, 1]2026.06 | 4.26 | — | — | — | — | |
| DRL (λ=1, R1=0)Model=RAE, Embedder=DINOv3-L, λ=1, R1=0, cfg=1.5, interval=[0, 1]2026.06 | 4.57 | — | — | — | — | |
| BaseModel=RAE, Embedder=DINOv3-L, λ=−−, R1=−−, cfg=1.5, interval=[0, 1]2026.06 | 4.83 | — | — | — | — | |
| DRL (λ*)Model=JiT, Embedder=DINOv3-L, λ=20, R1=10−5, cfg=3.25, interval=[.1, 1]2026.06 | 8.1 | — | — | — | — | |
| DRL (λ*)Model=RAE, Embedder=SigLIP-L, λ=10, R1=10−5, cfg=1.75, interval=[.1, 1]2026.06 | 9.06 | — | — | — | — | |
| DRL (λ*)Model=REPA, Embedder=SigLIP-L, λ=1, R1=10−5, cfg=3, interval=[.3, 1]2026.06 | 9.32 | — | — | — | — | |
| DRL (λ=1, R1=0)Model=RAE, Embedder=SigLIP-L, λ=1, R1=0, cfg=1.25, interval=[0, 1]2026.06 | 9.4 | — | — | — | — | |
| BaseModel=RAE, Embedder=SigLIP-L, λ=−−, R1=−−, cfg=1.25, interval=[0, 1]2026.06 | 9.5 | — | — | — | — | |
| BaseModel=REPA, Embedder=SigLIP-L, λ=−−, R1=−−, cfg=3.75, interval=[.3, 1]2026.06 | 9.52 | — | — | — | — | |
| DRL (λ=1, R1=0)Model=REPA, Embedder=SigLIP-L, λ=1, R1=0, cfg=2.25, interval=[.3, 1]2026.06 | 10.02 | — | — | — | — | |
| DRL (λ=1, R1=0)Model=JiT, Embedder=DINOv3-L, λ=1, R1=0, cfg=2.25, interval=[0, 1]2026.06 | 10.19 | — | — | — | — | |
| BaseModel=JiT, Embedder=DINOv3-L, λ=−−, R1=−−, cfg=2.75, interval=[0, 1]2026.06 | 10.89 | — | — | — | — | |
| DRL (λ*)Model=SiT, Embedder=SigLIP-L, λ=1, R1=10−5, cfg=2.75, interval=[.3, 1]2026.06 | 11.58 | — | — | — | — | |
| BaseModel=SiT, Embedder=SigLIP-L, λ=−−, R1=−−, cfg=3.5, interval=[.3, 1]2026.06 | 11.81 | — | — | — | — | |
| DRL (λ=1, R1=0)Model=SiT, Embedder=SigLIP-L, λ=1, R1=0, cfg=2.25, interval=[.3, 1]2026.06 | 12.17 | — | — | — | — | |
| DRL (λ*)Model=REPA, Embedder=DINOv3-L, λ=10, R1=10−5, cfg=2.25, interval=[.3, 1]2026.06 | 13.01 | — | — | — | — | |
| DRL (λ=1, R1=0)Model=REPA, Embedder=DINOv3-L, λ=1, R1=0, cfg=2.75, interval=[.1, 1]2026.06 | 14.58 | — | — | — | — | |
| DRL (λ*)Model=SiT, Embedder=DINOv3-L, λ=10, R1=10−5, cfg=2.25, interval=[.3, 1]2026.06 | 16.4 | — | — | — | — | |
| DRL (λ*)Model=JiT, Embedder=SigLIP-L, λ=5, R1=10−5, cfg=3, interval=[.1, 1]2026.06 | 16.47 | — | — | — | — | |
| DRL (λ=1, R1=0)Model=JiT, Embedder=SigLIP-L, λ=1, R1=0, cfg=3, interval=[.1, 1]2026.06 | 17.11 | — | — | — | — | |
| BaseModel=JiT, Embedder=SigLIP-L, λ=−−, R1=−−, cfg=3.5, interval=[.1, 1]2026.06 | 18.21 | — | — | — | — | |
| DRL (λ=1, R1=0)Model=SiT, Embedder=DINOv3-L, λ=1, R1=0, cfg=3, interval=[.1, 1]2026.06 | 18.32 | — | — | — | — | |
| BaseModel=REPA, Embedder=DINOv3-L, λ=−−, R1=−−, cfg=3.25, interval=[0, 1]2026.06 | 18.6 | — | — | — | — | |
| DRL (λ*)Model=RAE, Embedder=DINOv2-L, λ=5, R1=10−5, cfg=1.25, interval=[0, 1]2026.06 | 20.24 | — | — | — | — | |
| BaseModel=SiT, Embedder=DINOv3-L, λ=−−, R1=−−, cfg=3.5, interval=[0, 1]2026.06 | 21.63 | — | — | — | — | |
| DRL (λ=1, R1=0)Model=RAE, Embedder=DINOv2-L, λ=1, R1=0, cfg=1.25, interval=[0, 1]2026.06 | 23.66 | — | — | — | — | |
| BaseModel=RAE, Embedder=DINOv2-L, λ=−−, R1=−−, cfg=1.5, interval=[0, 1]2026.06 | 25.94 | — | — | — | — | |
| DRL (λ*)Model=JiT, Embedder=DINOv2-L, λ=10, R1=10−5, cfg=2.75, interval=[.1, 1]2026.06 | 30.64 | — | — | — | — | |
| DRL (λ=1, R1=0)Model=REPA, Embedder=DINOv2-L, λ=1, R1=0, cfg=2.75, interval=[.3, 1]2026.06 | 32.87 | — | — | — | — | |
| DRL (λ*)Model=REPA, Embedder=DINOv2-L, λ=1, R1=0, cfg=2.75, interval=[.3, 1]2026.06 | 32.87 | — | — | — | — | |
| DRL (λ=1, R1=0)Model=JiT, Embedder=DINOv2-L, λ=1, R1=0, cfg=3.5, interval=[.1, 1]2026.06 | 36.1 | — | — | — | — | |
| BaseModel=REPA, Embedder=DINOv2-L, λ=−−, R1=−−, cfg=2.75, interval=[.1, 1]2026.06 | 36.87 | — | — | — | — | |
| BaseModel=JiT, Embedder=DINOv2-L, λ=−−, R1=−−, cfg=4, interval=[.1, 1]2026.06 | 41.55 | — | — | — | — | |
| DRL (λ=1, R1=0)Model=SiT, Embedder=DINOv2-L, λ=1, R1=0, cfg=2.75, interval=[.3, 1]2026.06 | 42.36 | — | — | — | — | |
| DRL (λ*)Model=SiT, Embedder=DINOv2-L, λ=1, R1=0, cfg=2.75, interval=[.3, 1]2026.06 | 42.36 | — | — | — | — | |
| BaseModel=SiT, Embedder=DINOv2-L, λ=−−, R1=−−, cfg=2.75, interval=[.1, 1]2026.06 | 46.96 | — | — | — | — | |
| ADMtraining_dataset=ImageNet2026.02 | — | 79 | 89 | 29.74 | 2,279.73 | |
| BigGANtraining_dataset=ImageNet2026.02 | — | 44 | 57 | 26.91 | 1,655.41 | |
| GigaGANtraining_dataset=ImageNet2026.02 | — | 74 | 70 | 30.59 | 2,174.02 | |
| LDMtraining_dataset=ImageNet2026.02 | — | 76 | 93 | 34.13 | 2,155.19 | |
| RQ-Transformertraining_dataset=ImageNet2026.02 | — | 76 | 59 | 29.23 | 2,214.47 | |
| StyleGAN-XLtraining_dataset=ImageNet2026.02 | — | 74 | 96 | 31.27 | 2,209.83 |