List your company

Class-conditional image generation on ImageNet 15 (val)

1.36gFIDRAR-XXL(DINOv2)
0.12648.453216.7825.1068May 18, 2026

Evaluation results

MethodLinks
RAR-XXL(DINOv2)Type=AR., #Para.=1.5B, #Tok.=256, Generation Mode=w/ CFG2026.051.365.85301.37866
RAR-XL(DINOv2)Type=AR., #Epoch=400, #Para.=955M, #Tok.=256, Generation Mode=w/ CFG2026.051.385.86310.27865
RAR-XXL(SigLIP)Type=AR., #Para.=1.5B, #Tok.=256, Generation Mode=w/ CFG2026.051.386.18298.47865
RAR-XL(SigLIP)Type=AR., #Para.=955M, #Tok.=256, Generation Mode=w/ CFG2026.051.46.39311.77865
RAR-XXL(SigLIP2)Type=AR., #Para.=955M, #Tok.=256, Generation Mode=w/ CFG2026.051.436.072917965
RAR-L(DINOv2)Type=AR., #Para.=461M, #Tok.=256, Generation Mode=w/ CFG2026.051.446.03312.87866
RAR-L(SigLIP)Type=AR., #Epoch=400, #Para.=461M, #Tok.=256, Generation Mode=w/ CFG2026.051.466.18312.97864
RAR-XL(SigLIP2)Type=AR., #Para.=955M, #Tok.=256, Generation Mode=w/ CFG2026.051.466.02288.47865
RAR-XXLType=AR., #Para.=1.5B, #Tok.=256, Generation Mode=w/ CFG2026.051.48—3268063
RAR-XLType=AR., #Para.=955M, #Tok.=256, Generation Mode=w/ CFG2026.051.5—306.98062
RAR-L(SigLIP2)Type=AR., #Epoch=400, #Para.=461M, #Tok.=256, Generation Mode=w/ CFG2026.051.56.37292.77766
RAR-XXL(DINOv2)Type=AR., #Para.=1.5B, #Tok.=256, Generation Mode=w/o CFG2026.051.655.55253.78063
RAR-XXL(SigLIP2)Type=AR., #Para.=955M, #Tok.=256, Generation Mode=w/o CFG2026.051.655.44266.58163
RAR-XXL(SigLIP)Type=AR., #Para.=1.5B, #Tok.=256, Generation Mode=w/o CFG2026.051.685.64239.57963
RAR-LType=AR., #Epoch=400, #Para.=461M, #Tok.=256, Generation Mode=w/ CFG2026.051.7—299.58258
RAR-XL(SigLIP2)Type=AR., #Para.=955M, #Tok.=256, Generation Mode=w/o CFG2026.051.725.41244.88063
RAR-XL(DINOv2)Type=AR., #Epoch=400, #Para.=955M, #Tok.=256, Generation Mode=w/o CFG2026.051.745.332338063
SiT-XL/2+REPAType=Diff., #Epoch=1600, #Para.=675M, #Tok.=256, Generation Mode=w/ CFG2026.051.84.52848161
RAR-XL(SigLIP)Type=AR., #Para.=955M, #Tok.=256, Generation Mode=w/o CFG2026.051.875.77226.77963
VFMTok-2B(SigLIP)Type=AR., #Epoch=200, #Para.=2.2B, #Tok.=256, Generation Mode=w/o CFG2026.051.925.78260.58261
VFMTok-XXL(DINOv2)Type=AR., #Epoch=200, #Para.=1.4B, #Tok.=256, Generation Mode=w/o CFG2026.051.955.65259.38262
VFMTok-XXL(SigLIP2)Type=AR., #Epoch=200, #Para.=1.4B, #Tok.=256, Generation Mode=w/o CFG2026.051.985.53265.38262
VFMTok-2B(SigLIP2)Type=AR., #Epoch=200, #Para.=2.2B, #Tok.=256, Generation Mode=w/o CFG2026.051.985.41269.78262
RAR-L(DINOv2)Type=AR., #Para.=461M, #Tok.=256, Generation Mode=w/o CFG2026.052.025.51210.47963
FasterDITType=Diff., #Epoch=400, Generation Mode=w/ CFG2026.052.034.632648160
VFMTok-3B(DINOv2)Type=AR., #Epoch=200, #Para.=3.1B, #Tok.=256, Generation Mode=w/o CFG2026.052.045.43267.68261
VFMTok-2B(SigLIP)Type=AR., #Epoch=200, #Para.=2.2B, #Tok.=256, Generation Mode=w/ CFG2026.052.055.77271.48261
RAR-L(SigLIP2)Type=AR., #Epoch=400, #Para.=461M, #Tok.=256, Generation Mode=w/o CFG2026.052.055.5217.77962
SiT-XL/2Type=Diff., #Epoch=1600, #Para.=675M, #Tok.=256, Generation Mode=w/ CFG2026.052.064.5270.38259
VFMTok-3B(DINOv2)Type=AR., #Epoch=200, #Para.=3.1B, #Tok.=256, Generation Mode=w/ CFG2026.052.076.23280.48162
VFMTok-2B(DINOv2)Type=AR., #Epoch=200, #Para.=2.2B, #Tok.=256, Generation Mode=w/o CFG2026.052.085.49263.98261
VFMTok-2B(DINOv2)Type=AR., #Epoch=200, #Para.=2.2B, #Tok.=256, Generation Mode=w/ CFG2026.052.096.25274.58161
VFMTok-XXL(SigLIP)Type=AR., #Epoch=200, #Para.=1.4B, #Tok.=256, Generation Mode=w/ CFG2026.052.095.75272.68260
VFMTok-XXL(SigLIP)Type=AR., #Epoch=200, #Para.=1.4B, #Tok.=256, Generation Mode=w/o CFG2026.052.095.75272.68260
VFMTok-XL(DINOv2)Type=AR., #Para.=775M, #Tok.=256, Generation Mode=w/o CFG2026.052.15.54258.18260
VFMTok-L(DINOv2)Type=AR., #Para.=343M, #Tok.=256, Generation Mode=w/o CFG2026.052.115.46230.18260
VFMTok-L(SigLIP2)Type=AR., #Epoch=300, #Para.=343M, #Tok.=256, Generation Mode=w/o CFG2026.052.115.39225.68160
VFMTok-XXL(SigLIP2)Type=AR., #Epoch=200, #Para.=1.4B, #Tok.=256, Generation Mode=w/ CFG2026.052.165.452728360
VFMTok-2B(SigLIP2)Type=AR., #Epoch=200, #Para.=2.2B, #Tok.=256, Generation Mode=w/ CFG2026.052.175.43281.48360
LlamaGen-3BType=AR., #Para.=3.1B, #Tok.=576, Generation Mode=w/ CFG2026.052.195.97263.38258
VFMTok-XXL(DINOv2)Type=AR., #Epoch=200, #Para.=1.4B, #Tok.=256, Generation Mode=w/ CFG2026.052.195.532788360
RAR-L(SigLIP)Type=AR., #Epoch=400, #Para.=461M, #Tok.=256, Generation Mode=w/o CFG2026.052.265.78204.37962
DiTType=Diff., #Epoch=1600, #Para.=675M, #Tok.=256, Generation Mode=w/ CFG2026.052.274.6278.28357
MaskDiTType=Diff., #Epoch=1600, #Para.=675M, #Tok.=256, Generation Mode=w/ CFG2026.052.285.67276.68061
LlamaGen-XXLType=AR., #Para.=1.4B, #Tok.=576, Generation Mode=w/ CFG2026.052.346253.98160
VFMTok-XL(DINOv2)Type=AR., #Para.=775M, #Tok.=256, Generation Mode=w/ CFG2026.052.415.53276.88359
VFMTok-L(SigLIP)Type=AR., #Epoch=300, #Para.=343M, #Tok.=256, Generation Mode=w/ CFG2026.052.615.54272.18456
VFMTok-L(SigLIP)Type=AR., #Epoch=300, #Para.=343M, #Tok.=256, Generation Mode=w/o CFG2026.052.615.54272.18456
LlamaGen-XLType=AR., #Para.=775M, #Tok.=576, Generation Mode=w/ CFG2026.052.635.59244.18158
VFMTok-L(SigLIP2)Type=AR., #Epoch=300, #Para.=343M, #Tok.=256, Generation Mode=w/ CFG2026.052.695.31273.48456
VFMTok-L(DINOv2)Type=AR., #Para.=343M, #Tok.=256, Generation Mode=w/ CFG2026.052.755.58278.88457
LlamaGen-LType=AR., #Para.=343M, #Tok.=576, Generation Mode=w/ CFG2026.053.076.09256.18352
VFMTok-B(DINOv2)Type=AR., #Epoch=300, #Para.=111M, #Tok.=256, Generation Mode=w/o CFG2026.053.095.67173.68058
VARType=AR., #Epoch=350, #Para.=310M, #Tok.=680, Generation Mode=w/ CFG2026.053.3—274.48451
VFMTok-B(DINOv2)Type=AR., #Epoch=300, #Para.=111M, #Tok.=256, Generation Mode=w/ CFG2026.053.435.88252.28553
RAR-XXLType=AR., #Para.=1.5B, #Tok.=256, Generation Mode=w/o CFG2026.053.855.18176.27861
MaskGiT-reType=Mask., Generation Mode=w/ CFG, rejection sampling=true2026.054.02—355.6——
TiTok-LType=AR., #Para.=343M, #Tok.=256, re-implemented=true, Generation Mode=w/ CFG2026.054.036.93219.58452
RAR-XLType=AR., #Para.=955M, #Tok.=256, Generation Mode=w/o CFG2026.054.625.27158.37762
MaskDiTType=Diff., #Epoch=1600, #Para.=675M, #Tok.=256, Generation Mode=w/o CFG2026.055.6910.34177.97460
SiT-XL/2+REPAType=Diff., #Epoch=1600, #Para.=675M, #Tok.=256, Generation Mode=w/o CFG2026.055.9————
LlamaGen-BType=AR., #Epoch=300, #Para.=111M, #Tok.=576, Generation Mode=w/ CFG2026.056.097.24182.58542
MaskGiTType=Mask., #Epoch=555, #Para.=227M, #Tok.=256, Generation Mode=w/o CFG2026.056.18—182.18051
RAR-LType=AR., #Epoch=400, #Para.=461M, #Tok.=256, Generation Mode=w/o CFG2026.056.725.56129.27461
TiTok-BType=AR., #Epoch=300, #Para.=111M, #Tok.=256, re-implemented=true, Generation Mode=w/ CFG2026.056.767.82175.38543
FasterDITType=Diff., #Epoch=400, Generation Mode=w/o CFG2026.057.915.45131.36769
SiT-XL/2Type=Diff., #Epoch=1600, #Para.=675M, #Tok.=256, Generation Mode=w/o CFG2026.058.616.32131.76867
LlamaGen-3BType=AR., #Para.=3.1B, #Tok.=576, Generation Mode=w/o CFG2026.059.388.24112.96967
DiTType=Diff., #Epoch=1600, #Para.=675M, #Tok.=256, Generation Mode=w/o CFG2026.059.626.85121.56767
TiTok-LType=AR., #Para.=343M, #Tok.=256, re-implemented=true, Generation Mode=w/o CFG2026.0511.47.1488.86864
LlamaGen-XXLType=AR., #Para.=1.4B, #Tok.=576, Generation Mode=w/o CFG2026.0514.68.6986.36368
LlamaGen-XLType=AR., #Para.=775M, #Tok.=576, Generation Mode=w/o CFG2026.0515.57.0479.26269
LlamaGen-LType=AR., #Para.=343M, #Tok.=576, Generation Mode=w/o CFG2026.0519.18.6764.36167
TiTok-BType=AR., #Epoch=300, #Para.=111M, #Tok.=256, re-implemented=true, Generation Mode=w/o CFG2026.0519.67.5457.96460
LlamaGen-BType=AR., #Epoch=300, #Para.=111M, #Tok.=576, Generation Mode=w/o CFG2026.0532.211.8439.95761