Image Styling on Regular Dataset 1.0 (test)
85.41Overall ScoreDPO (D)
Evaluation results
| Method | Links | |||||||
|---|---|---|---|---|---|---|---|---|
| DPO (D)Modality=Vision, Model Scale=8B2026.03 | 85.41 | 87.12 | 82.97 | 85.51 | 83.98 | 87.03 | 85.68 | |
| Standardized Reward-Weighted (SW)Modality=Vision, Model Scale=8B2026.03 | 83.6 | 86.69 | 81.78 | 83.98 | 81.61 | 84.92 | 82.54 | |
| Reward-Weighted (RW)Modality=Vision, Model Scale=8B2026.03 | 83.55 | 86.69 | 81.27 | 84.07 | 80.85 | 85.93 | 82.63 | |
| Edit-Only (E)Modality=Vision, Model Scale=8B2026.03 | 83.38 | — | 84.07 | — | — | 83.81 | — | |
| BModality=Vision, Model Scale=8B2026.03 | 82.96 | 85.08 | 80.85 | 83.22 | 80.51 | 84.92 | 83.31 | |
| RModality=Vision, Model Scale=8B2026.03 | 82.9 | 85.59 | 80.93 | 83.9 | 80.51 | 84.24 | 82.2 | |
| SModality=Vision, Model Scale=8B2026.03 | 82.61 | 85.17 | 80.42 | 82.71 | 80.17 | 84.32 | 82.71 | |
| GPT-4o (G4o)Modality=Vision, Model Scale=N/A2026.03 | 77.66 | 78.39 | 77.12 | 79.15 | 75.34 | 77.37 | 78.73 |