Text-to-Image Factuality Evaluation on Culture 30
89.4FAGERFLUX1-dev + FAGER
Evaluation Results
| Method | Links | |
|---|---|---|
| FLUX1-dev + FAGERModel=FLUX1-dev, Refinement Backbone=Kontext2026.05 | 89.4 | |
| FLUX1-dev + FAGERModel=FLUX1-dev, Refinement Backbone=Qwen-Edit2026.05 | 87.97 | |
| Nano Banana ProModel=Nano Banana Pro2026.05 | 86.53 | |
| FLUX2-devModel=FLUX2-dev2026.05 | 83.36 | |
| Stable Diffusion 3.5 LargeModel=Stable Diffusion 3.5 Large2026.05 | 66.75 | |
| FLUX1-devModel=FLUX1-dev2026.05 | 60.19 |