Spatial Reasoning on Latent Diffusion Models reasoning evaluation set
73Human ScoreHumans
Evaluation results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| HumansText Encoder=T52023.11 | 73 | — | — | — | — | — | |
| HumansText Encoder=CLIP2023.11 | 21 | — | — | — | — | — | |
| CLIPScoreText Encoder=CLIP2023.11 | — | 0.75 | — | — | — | — | |
| CLIPScoreText Encoder=T52023.11 | — | 0.83 | — | — | — | — | |
| LLMScoreText Encoder=CLIP2023.11 | — | — | — | — | 21.4 | — | |
| LLMScoreText Encoder=T52023.11 | — | — | — | — | 23.1 | — | |
| MIDText Encoder=CLIP2023.11 | — | — | 433,000,000,000,000 | — | — | — | |
| MIDText Encoder=T52023.11 | — | — | -8,000,000,000,000,000 | — | — | — | |
| SELFEVALText Encoder=CLIP2023.11 | — | — | — | — | — | 33.4 | |
| SELFEVALText Encoder=T52023.11 | — | — | — | — | — | 35.8 | |
| VPEvalText Encoder=CLIP2023.11 | — | — | — | 34.1 | — | — | |
| VPEvalText Encoder=T52023.11 | — | — | — | 23.4 | — | — |