Text-to-Image Generation on DSG benchmark
6.48Aesthetic ScoreBeautifulPrompt
Evaluation results
| Method | Links | ||
|---|---|---|---|
| BeautifulPromptGenerative Model=Flux2025.06 | 6.48 | — | |
| VisualPrompter + NeuroPromptsGenerative Model=Flux2025.06 | 6.44 | — | |
| NeuroPromptsGenerative Model=Flux2025.06 | 6.4 | — | |
| PromptistGenerative Model=Flux2025.06 | 6.25 | — | |
| NeuroPromptsGenerative Model=SD v1.52025.06 | 6.21 | — | |
| VisualPrompter + NeuroPromptsGenerative Model=SD v2.12025.06 | 6.15 | — | |
| VisualPrompter + NeuroPromptsGenerative Model=SD v1.52025.06 | 6.13 | — | |
| NeuroPromptsGenerative Model=SD v2.12025.06 | 6.03 | — | |
| VisualPrompterGenerative Model=Flux2025.06 | 6.03 | — | |
| BeautifulPromptGenerative Model=SD v2.12025.06 | 5.98 | — | |
| BeautifulPromptGenerative Model=SD v1.52025.06 | 5.97 | — | |
| PromptistGenerative Model=SD v1.52025.06 | 5.93 | — | |
| PromptistGenerative Model=SD v2.12025.06 | 5.86 | — | |
| BaselineGenerative Model=Flux2025.06 | 5.77 | — | |
| VisualPrompterGenerative Model=SD v2.12025.06 | 5.73 | — | |
| VisualPrompterGenerative Model=SD v1.52025.06 | 5.66 | — | |
| BaselineGenerative Model=SD v2.12025.06 | 5.48 | — | |
| BaselineGenerative Model=SD v1.52025.06 | 5.3 | — | |
| BaselineGenerative Model=Average Across Models2025.06 | — | 5.52 | |
| BeautifulPromptGenerative Model=Average Across Models2025.06 | — | 6.14 | |
| NeuroPromptsGenerative Model=Average Across Models2025.06 | — | 6.21 | |
| PromptistGenerative Model=Average Across Models2025.06 | — | 6.01 | |
| VisualPrompterGenerative Model=Average Across Models2025.06 | — | 5.81 | |
| VisualPrompter + NeuroPromptsGenerative Model=Average Across Models2025.06 | — | 6.24 |