Text-to-Image Factuality Evaluation on I-HallA History
87.76FAGERNano Banana Pro
Evaluation Results
| Method | Links | |
|---|---|---|
| Nano Banana ProModel=Nano Banana Pro2026.05 | 87.76 | |
| FLUX1-dev + FAGERModel=FLUX1-dev, Refinement Backbone=Kontext2026.05 | 81.2 | |
| FLUX1-dev + FAGERModel=FLUX1-dev, Refinement Backbone=Qwen-Edit2026.05 | 79.44 | |
| FLUX2-devModel=FLUX2-dev2026.05 | 76.92 | |
| FLUX1-devModel=FLUX1-dev2026.05 | 74.58 | |
| Stable Diffusion 3.5 LargeModel=Stable Diffusion 3.5 Large2026.05 | 68.89 |