Image Editing on User Study 100 images (test)
94.3User Selection RateAlterbute
Evaluation Results
| Method | Links | |
|---|---|---|
| AlterbuteEvaluator=Gemini, Baseline=MimicBrush, Baseline Category=Attribute-specific Editor2026.01 | 94.3 | |
| AlterbuteEvaluator=Claude, Baseline=MimicBrush, Baseline Category=Attribute-specific Editor2026.01 | 92.6 | |
| AlterbuteEvaluator=Claude, Baseline=FlowEdit, Baseline Category=General Purpose Editor2026.01 | 92.6 | |
| AlterbuteEvaluator=GPT-4o, Baseline=MimicBrush, Baseline Category=Attribute-specific Editor2026.01 | 89.8 | |
| AlterbuteEvaluator=Gemini, Baseline=FlowEdit, Baseline Category=General Purpose Editor2026.01 | 89.6 | |
| AlterbuteEvaluator=User, Baseline=FlowEdit, Baseline Category=General Purpose Editor2026.01 | 89.3 | |
| AlterbuteEvaluator=Gemini, Baseline=InstructPix2Pix, Baseline Category=General Purpose Editor2026.01 | 88.8 | |
| AlterbuteEvaluator=GPT-4o, Baseline=FlowEdit, Baseline Category=General Purpose Editor2026.01 | 88.6 | |
| AlterbuteEvaluator=Gemini, Baseline=MaterialFusion, Baseline Category=Attribute-specific Editor2026.01 | 87 | |
| AlterbuteEvaluator=GPT-4o, Baseline=InstructPix2Pix, Baseline Category=General Purpose Editor2026.01 | 87 | |
| AlterbuteEvaluator=Gemini, Baseline=UltraEdit, Baseline Category=General Purpose Editor2026.01 | 86 | |
| AlterbuteEvaluator=Claude, Baseline=UltraEdit, Baseline Category=General Purpose Editor2026.01 | 85.6 | |
| AlterbuteEvaluator=Claude, Baseline=InstructPix2Pix, Baseline Category=General Purpose Editor2026.01 | 85.4 | |
| AlterbuteEvaluator=User, Baseline=MimicBrush, Baseline Category=Attribute-specific Editor2026.01 | 85 | |
| AlterbuteEvaluator=User, Baseline=InstructPix2Pix, Baseline Category=General Purpose Editor2026.01 | 85 | |
| AlterbuteEvaluator=Claude, Baseline=MaterialFusion, Baseline Category=Attribute-specific Editor2026.01 | 81.3 | |
| AlterbuteEvaluator=User, Baseline=OmniGen, Baseline Category=General Purpose Editor2026.01 | 81.2 | |
| AlterbuteEvaluator=Gemini, Baseline=OmniGen, Baseline Category=General Purpose Editor2026.01 | 80.2 | |
| AlterbuteEvaluator=User, Baseline=UltraEdit, Baseline Category=General Purpose Editor2026.01 | 80 | |
| AlterbuteEvaluator=User, Baseline=MaterialFusion, Baseline Category=Attribute-specific Editor2026.01 | 79.7 | |
| AlterbuteEvaluator=Claude, Baseline=OmniGen, Baseline Category=General Purpose Editor2026.01 | 78.8 | |
| AlterbuteEvaluator=GPT-4o, Baseline=UltraEdit, Baseline Category=General Purpose Editor2026.01 | 78.6 | |
| AlterbuteEvaluator=Claude, Baseline=Diptych, Baseline Category=General Purpose Editor2026.01 | 77.8 | |
| AlterbuteEvaluator=GPT-4o, Baseline=MaterialFusion, Baseline Category=Attribute-specific Editor2026.01 | 77.6 | |
| AlterbuteEvaluator=GPT-4o, Baseline=OmniGen, Baseline Category=General Purpose Editor2026.01 | 77.4 | |
| AlterbuteEvaluator=Gemini, Baseline=Diptych, Baseline Category=General Purpose Editor2026.01 | 76.8 | |
| AlterbuteEvaluator=User, Baseline=Diptych, Baseline Category=General Purpose Editor2026.01 | 76.2 | |
| AlterbuteEvaluator=GPT-4o, Baseline=Diptych, Baseline Category=General Purpose Editor2026.01 | 74.8 | |
| Null-text Inversion2022.11 | 65.1 | |
| Text2Live2022.11 | 16.6 | |
| SDEdit2022.11 | 14.5 | |
| VQGAN+CLIP2022.11 | 3.8 |