Text-to-Image Generation on HPD v3
11.91Characters ScoreFAIL-PD
Evaluation Results
| Method | Links | |||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| FAIL-PD2026.02 | 11.91 | 10.16 | 10.3 | 12.22 | 11.29 | 10.96 | 12.18 | 11.92 | 11.7 | 12 | 9.59 | 11.4 | 11.28 | |
| Kolors2026.02 | 11.79 | 10.47 | 9.87 | 10.82 | 10.6 | 9.89 | 10.68 | 10.93 | 10.5 | 10.63 | 11.06 | 9.51 | 10.55 | |
| FLUX.1 Dev2026.02 | 11.7 | 10.32 | 9.39 | 10.93 | 10.38 | 10.01 | 10.84 | 11.24 | 10.21 | 10.38 | 11.24 | 9.16 | 10.43 | |
| FAIL-PG2026.02 | 11.33 | 9.48 | 9.3 | 11.66 | 10.62 | 10.42 | 11.61 | 11.24 | 11.02 | 11.57 | 8.93 | 10.63 | 10.65 | |
| Infinity2026.02 | 11.17 | 9.95 | 9.43 | 10.36 | 9.27 | 10.11 | 10.36 | 10.59 | 10.08 | 10.3 | 10.59 | 9.62 | 10.26 | |
| Playground-v2.52026.02 | 11.07 | 9.84 | 9.64 | 10.45 | 10.38 | 9.94 | 10.51 | 10.62 | 10.15 | 10.62 | 10.84 | 9.39 | 10.27 | |
| CogView42026.02 | 10.72 | 9.86 | 9.33 | 9.88 | 9.16 | 9.45 | 9.69 | 9.86 | 9.45 | 9.49 | 10.16 | 8.97 | 9.61 | |
| PixArt-Σ2026.02 | 10.08 | 9.07 | 8.41 | 9.83 | 8.86 | 8.87 | 9.44 | 9.57 | 9.52 | 9.73 | 10.35 | 8.58 | 9.37 | |
| Gemini 2.0 Flash2026.02 | 9.98 | 8.44 | 7.64 | 10.11 | 9.42 | 9.01 | 9.74 | 9.64 | 9.55 | 10.16 | 7.61 | 9.23 | 9.21 | |
| Hunyuan-DiT2026.02 | 7.96 | 8.11 | 8.28 | 8.71 | 7.24 | 7.86 | 8.33 | 8.55 | 8.28 | 8.31 | 8.48 | 8.2 | 8.19 | |
| Wanda2025.07 | 3.46 | 3.61 | 3.23 | 3.83 | 3.38 | 3.84 | 3.64 | 3.2 | 3.41 | 3.37 | 3.33 | 3.56 | 3.49 | |
| Oursmitigation=adversarial fine-tuning2025.07 | 3.37 | 3.04 | 3.39 | 3.07 | 3.35 | 2.92 | 3.22 | 3.34 | 3.21 | 3.22 | 3.12 | 3.09 | 3.19 | |
| Ours+FTmitigation=adversarial fine-tuning, additional_fine_tuning=80k non-memorized images2025.07 | 2.85 | 2.72 | 2.84 | 2.58 | 2.9 | 2.55 | 2.79 | 2.79 | 2.71 | 2.78 | 2.71 | 2.62 | 2.74 | |
| NeMo2025.07 | 2.85 | 2.92 | 2.9 | 2.99 | 2.86 | 2.97 | 2.83 | 3 | 3.11 | 3.11 | 3.09 | 3.01 | 2.97 | |
| Clean2025.07 | 2.47 | 2.72 | 2.63 | 2.52 | 2.5 | 2.71 | 2.53 | 2.66 | 2.56 | 2.52 | 2.76 | 2.73 | 2.61 |