Cross-Task Visual In-Context Learning on Second-tier group Colorization to Style Transfer
13.35PSNRGemini 2.5 Flash
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| Gemini 2.5 FlashPrompting Strategy=Fixed2025.11 | 13.35 | 46.5 | 5.1 | |
| T2T-VICL (Gemini 2.5 Flash)Model=Gemini 2.5 Flash, Prompting Strategy=Ours2025.11 | 13.03 | 43.4 | 7.37 | |
| Seedream 4.0Prompting Strategy=Fixed2025.11 | 9.91 | 33.3 | 7.99 | |
| T2T-VICL (Seedream 4.0)Model=Seedream 4.0, Prompting Strategy=Ours2025.11 | 9.54 | 31.4 | 8.09 |