Text-to-Image Synthesis on Aesthetic-Eval 4K resolution (test)
146.33gFIDFlux-SGA-DINOv3
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| Flux-SGA-DINOv3Vision Foundation Model=DINOv32026.05 | 146.33 | 33.61 | 6.17 | 0.43 | 17.33 | |
| Flux-SGA-DINOv2Vision Foundation Model=DINOv22026.05 | 146.41 | 33.6 | 6.15 | 0.47 | 15.56 | |
| Flux-SGA-SAM2Vision Foundation Model=SAM22026.05 | 148.3 | 33.46 | 6.1 | 0.4 | 16.11 | |
| Flux-WLFBaseline=Diffusion-4K2026.05 | 151.95 | 33.12 | 6.08 | 0.39 | 18.69 | |
| Flux2026.05 | 154.96 | 30.76 | 6.02 | 0.38 | 18.83 |