Image Generation on Unspecified Multimodal Dataset
17.6FID ScoreVision-Enhanced LLM
Evaluation results
| Method | Links | ||
|---|---|---|---|
| Vision-Enhanced LLMComputational Efficiency (%)=802025.12 | 17.6 | 82 | |
| ImagenComputational Efficiency (%)=702025.12 | 22.8 | 78 | |
| Stable DiffusionComputational Efficiency (%)=652025.12 | 23.4 | 74 | |
| DALL·E 2Computational Efficiency (%)=622025.12 | 25.1 | 76 |