List your company

Class-conditional Image Generation on ImageNet-1k (train)

1.13FIDGAE
0.98281.97642.973.9636Nov 5, 2024Feb 5, 2025May 9, 2025Aug 10, 2025Nov 10, 2025Feb 11, 2026May 15, 2026

Evaluation results

MethodLinks
GAE# Params=675M, NFE=250 × 2, setup=Multi-NFE diffusion/flow2026.051.13
RAE + DiT-XL# Params=839M, NFE=50 × 2, setup=Multi-NFE diffusion/flow2026.051.13
REPA-E# Params=675M, NFE=250 × 2, setup=Multi-NFE diffusion/flow2026.051.15
LightningDiT-XL/2# Params=675M, NFE=250 × 2, setup=Multi-NFE diffusion/flow2026.051.35
SiT-XL/2 + REG# Params=675M, NFE=250 × 2, setup=Multi-NFE diffusion/flow2026.051.36
SiT-XL/2 + REPA# Params=675M, NFE=250 × 2, setup=Multi-NFE diffusion/flow2026.051.42
mmDiT-XL/2 (ours)Resolution=2562024.111.59
DiT-XL/2 w/AttImplementation=Our re-implementation, Resolution=2562024.111.71
mmDiT-XL/2 (SD3)Implementation=Our re-implementation, Resolution=2562024.111.71
iMF-XL/2# Params=610M, NFE=1, setup=1-NFE diffusion/flow from scratch2026.051.72
mDT-v2-XL/2 w/ LNResolution=2562024.111.79
DiT-XL/2 w/LNImplementation=Our re-implementation, Resolution=2562024.111.95
UNet (SDXL)Implementation=Our re-implementation, Resolution=2562024.112.05
PixArt-a-XL/2Implementation=Our re-implementation, Resolution=2562024.112.06
SiT-XL/2# Params=675M, NFE=250 × 2, setup=Multi-NFE diffusion/flow2026.052.06
Sphere Latent Encoder (Ours-XL/2)# Params=675M, NFE=6 × 2, setup=Sphere model2026.052.11
Sphere Latent Encoder (Ours-XL/2)# Params=675M, NFE=4 × 2, setup=Sphere model2026.052.25
DiT-XL2 w/ LNResolution=2562024.112.27
DiT-XL/2# Params=675M, NFE=250 × 2, setup=Multi-NFE diffusion/flow2026.052.27
mDT-v2-XL/2 w/ LNImplementation=Our re-implementation, Resolution=2562024.112.51
α-Flow-XL/2+# Params=676M, NFE=1, setup=1-NFE diffusion/flow from scratch2026.052.58
mmDiT-XL/2 (ours)Resolution=5122024.112.76
DiT-XL/2 w/LNImplementation=Our re-implementation, Resolution=5122024.112.85
mmDiT-XL/2 (SD3)Implementation=Our re-implementation, Resolution=5122024.113.02
DiT-XL2 w/ LNResolution=5122024.113.04
PixArt-a-XL/2Implementation=Our re-implementation, Resolution=5122024.113.05
MeanFlow-XL/2# Params=676M, NFE=1, setup=1-NFE diffusion/flow from scratch2026.053.43
UNet (SD/LDM-G4)Resolution=2562024.113.6
mDT-v2-XL/2 w/ LNImplementation=Our re-implementation, Resolution=5122024.113.75
Sphere Encoder# Params=1.3B, NFE=4 × 2, setup=Sphere model2026.054.02
UNet (SDXL)Implementation=Our re-implementation, Resolution=5122024.114.81