List your company

Class-conditional image generation on ImageNet 256x256 (train)

362ISIAR-XXL
274.848297.474320.1342.726Oct 10, 2023Mar 14, 2024Aug 18, 2024Jan 22, 2025Jun 28, 2025Dec 2, 2025May 8, 2026

Evaluation results

MethodLinks
IAR-XXLType=AR, #Para.=1.4B, CFG=2.52025.013623.74—8654———————
VAR-d30-reType=VAR, Epoch=350, #Params=2.0B, rejection sampling=True, Classifier-free guidance=True2024.06356.41.8—8357———————
MaskGIT-reType=Mask., Epoch=300, #Params=227M, Gflops=300, rejection sampling=True, Classifier-free guidance=True2024.06355.64.02——————————
MaskGIT-reType=Mask, #Para.=227M2025.01355.64.02——————————
VAREpochs=350, Params=2.0B, Guidance=true2025.12350.2——8260———1.73———
LEGO-XL-UArchitecture=Transformer, Classifier-free guidance=true2023.10338.082.594.218356350——————
LEGO-XL-UArchitecture=Transformer, Classifier-free guidance=false2023.10337.855.284.916765350——————
VAR-d30Type=VAR, Epoch=350, #Params=2.0B, Classifier-free guidance=True2024.06334.71.97—8161———————
MaskBitType=Mask., Epoch=1080, #Params=305M, Classifier-free guidance=True2024.06328.61.52——————————
MaskBit# Params(G)=305M, Tok. Model=LFQ, Token Type=2D, # Params(T)=54M, # Tokens=256, CFG=true2026.03328.6———————1.521.61——
RQTran-reType=AR, Epoch=50, #Params=3.8B, rejection sampling=True, Classifier-free guidance=True2024.06323.73.8——————————
RQTran.-reType=AR, #Para.=3.8B2025.01323.73.8——————————
RQ-Trans.# Params(G)=3.8B, Tok. Model=RQ, Token Type=2D, # Params(T)=66M, # Tokens=256, CFG=true2026.03323.7———————3.83.2——
VAREpochs=350, Params=2.0B, Guidance=false2025.12323.1——8259———1.92———
VAR# Params(G)=2B, Tok. Model=MSRQ, Token Type=2D, # Params(T)=109M, # Tokens=680, CFG=true2026.03323.1——7563———1.920.9——
REGEpochs=80, #Params=677M, Classifier-Free Guidance (CFG)=true2025.12321.41.864.497663———————
VAR-d24Type=VAR, Epoch=350, #Params=1.0B, Classifier-free guidance=True2024.06320.12.33—8257———————
MAGVIT-v2#params=307M, Guidance=w/ Guidance2023.12319.41.78——————————
FlexVAR-d24 w/ SAREpochs=+ 10, Param=1.0B, Step=10, Time=0.52025.12315.52.14—8159———————
REPA-EEpochs=800, #Params=675M, Classifier-Free Guidance (CFG)=true2025.12314.91.264.117966———————
REPA-EEpochs=800, Params=675M, Guidance=true2025.12314.9——7966———1.26———
MDTv2-XL/2#params=676M, Guidance=w/ Guidance2023.12314.71.58——————————
MDTv2-GType=Mask. + Diff., Epoch=919, #Params=675M, Gflops=119, Classifier-free guidance=True2024.06314.71.58—7965———————
MDTv2Epochs=1080, #Params=675M, Classifier-Free Guidance (CFG)=true2025.12314.71.584.527965———————
MDTv2Epochs=1080, Params=675M, Guidance=true2025.12314.7——7965———1.58———
MDTv2-XL/2# Params(G)=676M, Tok. Model=KL, Token Type=2D, # Params(T)=55M, # Tokens=4096, CFG=true2026.03314.7——7965———1.580.27——
VAR-d24Epochs=350, Param=1.0B, Step=10, Time=0.52025.12312.92.33—8259———————
MAETok# Params(G)=675M, Tok. Model=AE, Token Type=1D, # Params(T)=176M, # Tokens=128, CFG=true2026.03311.2——8163———1.670.48——
DDTEpochs=400, Params=675M, Guidance=true2025.12310.6——7965———1.26———
MacTok+SiT-XL# Params(G)=675M, Tok. Model=KL, Token Type=1D, # Params(T)=176M, # Tokens=64, CFG=true2026.03310.4——7866———1.580.75——
MacTok+LightningDiT# Params(G)=675M, Tok. Model=KL, Token Type=1D, # Params(T)=176M, # Tokens=64, CFG=true2026.03307.3——7766———1.680.75——
VAR-d20Type=VAR, Epoch=250, #Params=600M, Classifier-free guidance=True2024.06306.12.95—8453———————
SD-VAE + SiT-XL/2+REPATokenizer Type=2D, Tokenizer Param.=84M, rFID=0.62, Generator Type=Diff, Generator Param.=675M, # Tokens=1024, Resolution=256x2562026.01305.71.42—8065———————
REPAEpochs=800, #Params=675M, Classifier-Free Guidance (CFG)=true2025.12305.71.424.78065———————
REPAEpochs=800, Params=675M, Guidance=true2025.12305.7——8064———1.42———
SiT-XL/2 + REPA# Params(G)=675M, Tok. Model=KL, Token Type=2D, # Params(T)=84M, # Tokens=1024, CFG=true2026.03305.7——8259———1.420.62——
REPAArchitecture=Representation-Guided DiT, Generator Params=675M, Epochs=80, Guidance=with Guidance2026.05305.7——8065———1.420.61——
SpectralAR + SpectralAR-d20Tokenizer Type=Flex, rFID=4.03, Generator Type=AR, Generator Param.=600M, # Tokens=64, Resolution=256x2562026.01305.42.49——————————
l-DeTokEpochs=800, Params=479M, Guidance=true2025.12304.1——8162———1.35———
l-DeTok# Params(G)=479M, Tok. Model=KL, Token Type=2D, # Params(T)=172M, # Tokens=256, CFG=true2026.03304.1——8162———1.350.62——
MAREpochs=800, Params=943M, Guidance=true2025.12303.7——8162———1.55———
MAR-H# Params(G)=943M, Tok. Model=KL, Token Type=2D, # Params(T)=66M, # Tokens=256, CFG=true2026.03303.7——8162———1.551.22——
TexTok-256# Params(G)=675M, Tok. Model=KL, Token Type=1D, # Params(T)=176M, # Tokens=256, CFG=true2026.03303.1——7964———1.460.73——
VAR-d20Category=Autoregressive Model, # Avg. Activated Params.=600M2025.03302.62.57—8356———————
VAR + VAR-d20Tokenizer Type=2D, Tokenizer Param.=109M, rFID=0.9, Generator Type=VAR, Generator Param.=600M, # Tokens=680, Resolution=256x2562026.01302.62.57—8356———————
VAR-d20Epochs=250, Param=600M, Step=10, Time=0.32025.12302.62.95—8356———————
MacTok+SiT-XL# Params(G)=675M, Tok. Model=KL, Token Type=1D, # Params(T)=176M, # Tokens=128, CFG=true2026.03302.5——7966———1.440.43——
RCG, conditional (MAGE-L)#params=512M, Guidance=w/ Guidance2023.12300.72.25——————————
MacTok+LightningDiT# Params(G)=675M, Tok. Model=KL, Token Type=1D, # Params(T)=176M, # Tokens=128, CFG=true2026.03299.8——7867———1.50.43——
FlexVAR-d20Epochs=250, Param=600M, Step=10, Time=0.32025.12299.32.41—8558———————
FlexVAR-d24Epochs=350, Param=1.0B, Step=10, Time=0.52025.12299.12.21—8359———————
PixNerdEpochs=160, #Params=700M, Classifier-Free Guidance (CFG)=true2025.122972.154.557959———————
PixNerdEpochs=160, Params=700M, Guidance=true2025.12297——7959———2.15———
REGEpochs=480, #Params=677M, Classifier-Free Guidance (CFG)=true2025.12296.91.44.247766———————
PAE (DINOv2)Architecture=Representation-Native DiT, Generator Params=675M, Epochs=800, Guidance=with Guidance2026.05296.9——7967———1.030.26——
VA-VAE + LightningDiTTokenizer Type=2D, Tokenizer Param.=70M, rFID=0.28, Generator Type=Diff, Generator Param.=675M, # Tokens=256, Resolution=256x2562026.01295.31.35—7965———————
LightningDiTEpochs=800, #Params=675M, Classifier-Free Guidance (CFG)=true2025.12295.31.354.157965———————
VA-VAEEpochs=800, Params=675M, Guidance=true2025.12295.3——7965———1.35———
LightningDiT# Params(G)=675M, Tok. Model=KL, Token Type=2D, # Params(T)=70M, # Tokens=256, CFG=true2026.03295.3———————1.350.28——
ReDiArchitecture=Representation-Guided DiT, Generator Params=675M, Epochs=800, Guidance=with Guidance2026.05295.1——7864———1.610.58——
ImageFolder + ImageFolder-VARTokenizer Type=2D, Tokenizer Param.=176M, rFID=0.8, Generator Type=VAR, Generator Param.=362M, # Tokens=286, Resolution=256x2562026.012952.6—7563———————
ImageFolder# Params(G)=362M, Tok. Model=MSRQ, Token Type=1D, # Params(T)=176M, # Tokens=286, CFG=true2026.03295——7563———2.60.8——
AFMEpochs=800, Params=675M, Guidance=true2025.12293.6——7965———1.37———
FlexVAR-d20 w/ SAREpochs=+ 10, Param=600M, Step=10, Time=0.32025.12293.32.35—8259———————
TREADEpochs=740, #Params=675M, Classifier-Free Guidance (CFG)=true2025.12292.71.694.738163———————
JiTEpochs=600, Params=2.0B, Guidance=true2025.12292.6———————1.82———
DiMR-G/2RType=Diff., Epoch=800, #Params=1.1B, Gflops=331, Classifier-free guidance=True2024.06292.51.63—7963———————
FlexVAR-d16Epochs=180, Param=310M, Step=10, Time=0.22025.12291.33.05—8352———————
RecTokEpochs=600, Params=839M, Guidance=true2025.12289.2——7967———1.13———
LEGO-XL-PGArchitecture=Transformer, Classifier-free guidance=true2023.10289.122.054.778455512——————
DiMR-XL/2RType=Diff., Epoch=800, #Params=505M, Gflops=160, Classifier-free guidance=True2024.062891.7—7963———————
PAE (SigLIP2)Architecture=Representation-Native DiT, Generator Params=675M, Epochs=800, Guidance=with Guidance2026.05287.4——7768———1.070.27——
DiMR-XL/2RType=Diff., Epoch=400, #Params=505M, Gflops=160, Classifier-free guidance=True2024.06285.71.77—7962———————
DiffMoE-L-E8-DDPM-GCategory=Diffusion Model, Guidance=with, cfg=1.5, Sampling=DDPM, # Avg. Activated Params.=458M2025.03284.782.3—8259———————
DiffMoE-L-E8-DDPM-GAvg. Activated Params=458M, Diffusion Paradigm=DDPM, Guidance=with guidance, cfg=1.5, Training Steps=7000K2025.03284.782.3—8259———————
LEGO-XL-PRArchitecture=Transformer, Classifier-free guidance=true2023.10284.732.355.218360512——————
MDT-XL/2Architecture=Transformer, Classifier-free guidance=true2023.10283.011.794.5781601,664——————
MDT-GType=Mask. + Diff., Epoch=1299, #Params=676M, Gflops=119, Classifier-free guidance=True2024.062831.79—8161———————
SpectralAR + SpectralAR-d16Tokenizer Type=Flex, rFID=4.03, Generator Type=AR, Generator Param.=310M, # Tokens=64, Resolution=256x2562026.01282.23.02—8155———————
PixelFlowEpochs=320, #Params=677M, Classifier-Free Guidance (CFG)=true2025.12282.11.985.838160———————
PixelFlowEpochs=320, Params=677M, Guidance=true2025.12282.1——8160———1.98———
TiTok-S-128Type=Mask., Epoch=800, #Params=287M, Classifier-free guidance=True2024.06281.81.97——————————
TiTok-S + MaskGIT-UViT-LTokenizer Type=1D, Tokenizer Param.=72M, rFID=1.71, Generator Type=Mask, Generator Param.=287M, # Tokens=128, Resolution=256x2562026.01281.81.87——————————
TiTok-S-128# Params(G)=287M, Tok. Model=VQ, Token Type=1D, # Params(T)=72M, # Tokens=128, CFG=true2026.03281.8———————1.971.61——
VAE + MAR-BTokenizer Type=2D, Tokenizer Param.=66M, rFID=0.53, Generator Type=AR+Diff, Generator Param.=208M, # Tokens=256, Resolution=256x2562026.01281.72.31—8257———————
VAR-d16Epochs=180, Param=310M, Step=10, Time=0.22025.12280.43.55—8451———————
VQGAN-reType=AR, Epoch=100, #Params=1.4B, rejection sampling=True, Classifier-free guidance=True2024.06280.35.2——————————
VQGAN-reType=AR, #Para.=1.4B2025.01280.35.2——————————
Dense-DiT-XL-DDPM-G (reproduced)Category=Diffusion Model, Guidance=with, cfg=1.5, Sampling=DDPM, Reproduction=true, # Avg. Activated Params.=675M2025.03279.182.32—8357———————
Dense-DiT-XL-DDPM-GAvg. Activated Params=675M, Diffusion Paradigm=DDPM, Guidance=with guidance, cfg=1.5, Training Steps=7000K, Source=Our reproduction2025.03279.182.32—8357———————
SoftVQ-VAE# Params(G)=675M, Tok. Model=SoftVQ, Token Type=1D, # Params(T)=176M, # Tokens=64, CFG=true2026.03279——8063———1.780.88——
IAR-XXLType=AR, #Para.=1.4B, CFG=1.72025.01278.92.19—8158———————
DiT-XL/2Architecture=Transformer, Classifier-free guidance=true2023.10278.242.274.683571,792——————
DiT-XL/2Depth=28, #Param=675 M, Iters=7,000 K2024.12278.242.274.68357——6.91————
DiT-XL/2#params=675M, Guidance=w/ Guidance2023.12278.22.27——————————
DiT-XL/2Type=Diff., Epoch=1399, #Params=675M, Gflops=119, Classifier-free guidance=True2024.06278.22.27—8357———————
DiT-XL/2Type=Diffusion, #Para.=675M2025.01278.22.27—8357———————
Dense-DiT-XL-DDPM-GCategory=Diffusion Model, Guidance=with, cfg=1.5, Sampling=DDPM, Source=Peebles & Xie, 2023a, # Avg. Activated Params.=675M2025.03278.22.27—8357———————
Dense-DiT-XL-DDPM-GAvg. Activated Params=675M, Diffusion Paradigm=DDPM, Guidance=with guidance, cfg=1.5, Training Steps=7000K, Source=Original (Peebles & Xie, 2023a)2025.03278.22.27—8357———————
SD-VAE + DiT-XL/2Tokenizer Type=2D, Tokenizer Param.=84M, rFID=0.62, Generator Type=Diff, Generator Param.=675M, # Tokens=1024, Resolution=256x2562026.01278.22.27—8357———————