List your company
ResearchFormerly WizWand

Text-to-image generation on DPGBench (Overall)

86.58DPGBench Overall ScoreSeGroS
70.012874.313978.61582.9161Mar 20, 2026
Updated 7mo ago

Evaluation results

MethodLinks
SeGroSUMM=Harmon-1.5B, Fine-Tuning Dataset=BLIP3o-60k Dataset2026.0386.58
RecaUMM=Harmon-1.5B, Fine-Tuning Dataset=BLIP3o-60k Dataset2026.0386.5
SFT*UMM=Harmon-1.5B, Fine-Tuning Dataset=BLIP3o-60k Dataset2026.0385.6
SeGroSUMM=Harmon-0.5B, Fine-Tuning Dataset=MidjourneyV6 Dataset2026.0385.4
SeGroSUMM=Show-o-512, Fine-Tuning Dataset=MidjourneyV6 Dataset2026.0385.18
RecaUMM=Show-o-512, Fine-Tuning Dataset=MidjourneyV6 Dataset2026.0384.94
RecaUMM=Harmon-0.5B, Fine-Tuning Dataset=MidjourneyV6 Dataset2026.0384.67
SeGroSUMM=OpenUni-3.6B, Fine-Tuning Dataset=MidjourneyV6 Dataset2026.0383.37
RecaUMM=OpenUni-3.6B, Fine-Tuning Dataset=MidjourneyV6 Dataset2026.0382.75
SFT*UMM=Harmon-0.5B, Fine-Tuning Dataset=MidjourneyV6 Dataset2026.0382.5
w/o SFTUMM=Show-o-512, Fine-Tuning Dataset=MidjourneyV6 Dataset2026.0382.21
SFT*UMM=Show-o-512, Fine-Tuning Dataset=MidjourneyV6 Dataset2026.0381.8
SeGroSUMM=OpenUni-1.6B, Fine-Tuning Dataset=MidjourneyV6 Dataset2026.0381.33
w/o SFTUMM=Harmon-1.5B, Fine-Tuning Dataset=BLIP3o-60k Dataset2026.0380.93
RecaUMM=OpenUni-1.6B, Fine-Tuning Dataset=MidjourneyV6 Dataset2026.0380.45
SFT*UMM=OpenUni-3.6B, Fine-Tuning Dataset=MidjourneyV6 Dataset2026.0380.45
w/o SFTUMM=Harmon-0.5B, Fine-Tuning Dataset=MidjourneyV6 Dataset2026.0380.12
SFT*UMM=OpenUni-1.6B, Fine-Tuning Dataset=MidjourneyV6 Dataset2026.0379.7
w/o SFTUMM=OpenUni-3.6B, Fine-Tuning Dataset=MidjourneyV6 Dataset2026.0379.02
SeGroSUMM=Show-o-256, Fine-Tuning Dataset=MidjourneyV6 Dataset2026.0376.52
w/o SFTUMM=OpenUni-1.6B, Fine-Tuning Dataset=MidjourneyV6 Dataset2026.0376.29
RecaUMM=Show-o-256, Fine-Tuning Dataset=MidjourneyV6 Dataset2026.0375.7
SFT*UMM=Show-o-256, Fine-Tuning Dataset=MidjourneyV6 Dataset2026.0374.6
w/o SFTUMM=Show-o-256, Fine-Tuning Dataset=MidjourneyV6 Dataset2026.0370.65