Text-to-Image Generation on VISOR
77.28OA (%)InfSplign
Evaluation Results
| Method | Links | |||||||
|---|---|---|---|---|---|---|---|---|
| InfSplignBase Model=Stable Diffusion 2.1, Fine-tuning=false, Extra Input=false2025.12 | 77.28 | 76.26 | 98.68 | 94.65 | 86.66 | 73.48 | 50.23 | |
| CoMPaSSBase Model=Stable Diffusion 2.1, Fine-tuning=true, Extra Input=false2025.12 | 68.22 | 62.06 | 90.96 | 85.02 | 71.29 | 56.03 | 35.9 | |
| InfSplignBase Model=Stable Diffusion 1.4, Fine-tuning=false, Extra Input=false2025.12 | 67.36 | 66.54 | 98.79 | 90.48 | 77.79 | 61.37 | 36.54 | |
| CoMPaSSBase Model=Stable Diffusion 1.4, Fine-tuning=true, Extra Input=false2025.12 | 65.56 | 57.41 | 87.58 | 83.23 | 67.53 | 49.99 | 28.91 | |
| STORMBase Model=Stable Diffusion 2.1, Fine-tuning=false, Extra Input=false2025.12 | 62.55 | 59.35 | 94.88 | 88.34 | 71.75 | 52.03 | 25.42 | |
| STORMBase Model=Stable Diffusion 1.4, Fine-tuning=false, Extra Input=false2025.12 | 61.01 | 57.58 | 94.39 | 85.93 | 69.71 | 49.01 | 25.7 | |
| CONFORMBase Model=Stable Diffusion 1.4, Fine-tuning=false, Extra Input=false2025.12 | 60.73 | 38.48 | 62.33 | 73.01 | 45.82 | 25.57 | 9.52 | |
| SPRIGHTBase Model=Stable Diffusion 2.1, Fine-tuning=true, Extra Input=false2025.12 | 60.68 | 42.23 | 71.24 | 71.78 | 51.88 | 33.09 | 16.15 | |
| INITNOBase Model=Stable Diffusion 1.4, Fine-tuning=false, Extra Input=false2025.12 | 60.4 | 35.18 | 58.24 | 71.2 | 42.71 | 20.09 | 6.72 | |
| REVISIONBase Model=Stable Diffusion 1.4, Fine-tuning=false, Extra Input=true2025.12 | 53.96 | 52.71 | 97.69 | 77.79 | 61.02 | 44.9 | 27.15 | |
| Control-GPTBase Model=Stable Diffusion 1.4, Fine-tuning=true, Extra Input=true2025.12 | 48.33 | 44.17 | 65.97 | 69.8 | 51.2 | 35.67 | 20.48 | |
| REVISIONBase Model=Stable Diffusion 2.1, Fine-tuning=false, Extra Input=true2025.12 | 48.26 | 47.11 | 97.61 | 76.07 | 55.75 | 37.1 | 19.53 | |
| SD 2.1Base Model=Stable Diffusion 2.1, Extra Input=false2025.12 | 47.83 | 30.25 | 63.24 | 64.42 | 35.74 | 16.13 | 4.7 | |
| Divide-and-BindBase Model=Stable Diffusion 1.4, Fine-tuning=false, Extra Input=false2025.12 | 46.03 | 31.62 | 68.7 | 64.72 | 37.82 | 18.64 | 5.3 | |
| Attend-and-ExciteBase Model=Stable Diffusion 1.4, Fine-tuning=false, Extra Input=false2025.12 | 42.07 | 25.75 | 61.21 | 49.29 | 19.33 | 4.56 | 0.08 | |
| Layout GuidanceBase Model=Stable Diffusion 1.4, Fine-tuning=false, Extra Input=true2025.12 | 40.01 | 38.8 | 95.95 | — | — | — | — | |
| SD 1.4Base Model=Stable Diffusion 1.4, Fine-tuning=false, Extra Input=false2025.12 | 29.86 | 18.81 | 62.98 | 46.6 | 20.11 | 6.89 | 1.63 | |
| Structure DiffusionBase Model=Stable Diffusion 1.4, Fine-tuning=false, Extra Input=false2025.12 | 28.65 | 17.87 | 62.36 | 44.7 | 18.73 | 6.57 | 1.46 | |
| SD 1.4 + CDMBase Model=Stable Diffusion 1.4, Fine-tuning=true, Extra Input=false2025.12 | 23.27 | 14.99 | 64.41 | 39.44 | 14.56 | 4.84 | 1.12 | |
| GLIDE + CDMBase Model=Stable Diffusion 1.4, Fine-tuning=true, Extra Input=false2025.12 | 10.17 | 6.43 | 63.21 | 20.07 | 4.69 | 0.83 | 0.11 | |
| GLIDEBase Model=Stable Diffusion 1.4, Fine-tuning=true, Extra Input=false2025.12 | 3.36 | 1.98 | 59.06 | 6.72 | 1.02 | 0.17 | 0.03 |