Text-to-Image Generation on Unspecified Dataset (test)
12.5Training Time (hrs)Vision-Enhanced LLM
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| Vision-Enhanced LLMOptimization=Rectified flow2025.12 | 12.5 | 52 | 18.3 | |
| Imagen2025.12 | 13.6 | 69 | 21.8 | |
| DALL·E 22025.12 | 14.8 | 78 | 22.5 | |
| Stable Diffusion2025.12 | 15.2 | 85 | 24.7 |