List your company

Image Reconstruction on MS-COCO 2017 (val)

1.8rFIDMergeTok-BL (VAE)
1.39324.13916.8859.6309Dec 3, 2024Mar 3, 2025Jun 1, 2025Aug 31, 2025Nov 29, 2025Feb 27, 2026May 29, 2026

Evaluation results

MethodLinks
MergeTok-BL (VAE)Type=1D VAE+VQ, #Tok.=256, #Code=2^14, Res.=2562026.051.8—22.30.7
MergeTok-BL (VQ)Type=1D VAE+VQ, #Tok.=256, #Code=2^14, Res.=2562026.052.4—21.70.68
GigaTok-BLType=1D VQ, #Tok.=256, #Code=2^14, Res.=2562026.052.6—21.50.68
MergeTok-BL (VAE)Type=1D VAE+VQ, #Tok.=256, #Code=2^14, Res.=5122026.052.9—22.80.71
MergeTok-BL (VQ)Type=1D VAE+VQ, #Tok.=256, #Code=2^14, Res.=5122026.053.6—22.10.69
GigaTok-SBType=1D VQ, #Tok.=256, #Code=2^14, Res.=2562026.053.8—20.90.66
UniTokRatio=16, Resolution=256x2562026.054.05—23.920.73
GigaTok-BLType=1D VQ, #Tok.=256, #Code=2^14, Res.=5122026.054.2—21.90.69
WinTokRatio=16, Resolution=256x2562026.054.24—23.830.72
WeTokResolution=Original Resolution, Ratio=162026.025.3—21.940.59
SD-VAE 1.xResolution=Original Resolution, Ratio=82026.025.94—21.680.64
UniWeTokResolution=Resize 256 x 256, Ratio=322026.026.18—22.580.66
UniWeTokResolution=Original Resolution, Ratio=322026.026.46—22.290.65
WeTokResolution=Resize 256 x 256, Ratio=162026.026.55—21.990.63
WeTokRatio=16, Resolution=256x2562026.056.55—21.990.63
Open-MAGVIT2-I-PTResolution=Original Resolution, Ratio=162026.026.65—21.610.57
Open-MAGVIT2Ratio=16, Codebook Size=262144, Zero-shot=true2024.126.76—22.310.65
IBQRatio=16, Codebook Size=262144, Zero-shot=true2024.126.79—22.280.65
CosmosResolution=Original Resolution, Ratio=162026.027.23—20.450.53
IBQRatio=16, Codebook Size=16384, Zero-shot=true2024.127.67—21.580.62
Open-MAGVIT2Ratio=16, Codebook Size=16384, Zero-shot=true2024.127.93—22.210.62
Open-MAGVIT2-I-PTResolution=Resize 256 x 256, Ratio=162026.027.93—22.210.62
Open-MAGVIT2-I-PTRatio=16, Resolution=256x2562026.057.93—22.210.62
LlamaGenRatio=16, Codebook Size=16384, Zero-shot=true, Initial Training=Pre-trained on ImageNet2024.128.4—20.280.55
LlamaGenResolution=Resize 256 x 256, Ratio=162026.028.4—20.280.55
LlamaGenRatio=16, Resolution=256x2562026.058.4—20.280.55
WeTokResolution=Resize 256 x 256, Ratio=322026.028.94—20.310.55
WeTokResolution=Original Resolution, Ratio=322026.028.94—20.310.55
Show-oRatio=16, Codebook Size=8192, Zero-shot=true2024.129.26—20.90.59
Show-oResolution=Resize 256 x 256, Ratio=162026.029.26—20.90.59
Show-oRatio=16, Resolution=256x2562026.059.26—20.90.59
CosmosRatio=16, Codebook Size=64000, Zero-shot=true2024.1211.97—19.220.48
CosmosResolution=Resize 256 x 256, Ratio=162026.0211.97—19.220.48
DDIMConditioning=UC, Steps=502022.11—0.03——
DDIMConditioning=UC, Steps=2002022.11—0.023——
DDIMConditioning=C, Steps=502022.11—0.42——
DDIMConditioning=C, Steps=2002022.11—0.497——
EDICTConditioning=UC, Steps=502022.11—0.015——
EDICTConditioning=UC, Steps=2002022.11—0.015——
EDICTConditioning=C, Steps=502022.11—0.015——
EDICTConditioning=C, Steps=2002022.11—0.015——
LDM AESteps=502022.11—0.015——
LDM AESteps=2002022.11—0.015——