List your company

Image Reconstruction on ImageNet 512x512

0.2rFIDWAN2.2 VAE
-3.821623.324250.4777.6158Oct 14, 2024Jan 22, 2025May 3, 2025Aug 12, 2025Nov 21, 2025Mar 2, 2026Jun 11, 2026

Evaluation results

MethodLinks
WAN2.2 VAEResolution=5122026.060.230.480.9—
DC-AESetting (f/c)=f64c128, Latent Shape=8x8x1282024.100.2226.150.710.08
DC-AESetting (f/c)=f128c512, Latent Shape=4x4x5122024.100.2325.730.70.084
RepViTokResolution=5122026.060.23310.92—
ViTokResolution=5122026.060.2430.770.92—
IBQDynamic Resolution=supported, Dynamic Tokens=unsupported, Tokens=16x‡2026.040.4———
Open-MAGVIT-v2Dynamic Resolution=supported, Dynamic Tokens=unsupported, Tokens=16x‡2026.040.5———
VibeToken-LLDynamic Resolution=supported, Dynamic Tokens=supported, Tokens=32–2562026.040.51———
VibeToken-SLDynamic Resolution=supported, Dynamic Tokens=supported, Tokens=32–2562026.040.55———
LLaMAGen-TokDynamic Resolution=supported, Dynamic Tokens=unsupported, Tokens=16x‡2026.040.7———
DA-HTDynamic Resolution=supported, Dynamic Tokens=unsupported, Tokens=32x‡2026.040.83———
InstellaDynamic Resolution=supported, Dynamic Tokens=unsupported, Tokens=1282026.041.32———
TiTok-BDynamic Resolution=unsupported, Dynamic Tokens=unsupported, Tokens=64/128, resolution-specific training=true2026.041.52———
SD-VAESetting (f/c)=f64c128, Latent Shape=8x8x1282024.1016.8419.490.480.282
SD-VAESetting (f/c)=f128c512, Latent Shape=4x4x5122024.10100.7415.90.40.531