Image Generation on TextAtlasEval
Metric: TextScenesHQ Clip Score (higher is better)
Metric: TextScenesHQ Clip Score (higher is better)
| # | Model↕ | TextScenesHQ Clip Score▼ | Extra Data | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | Dalle3 | 0.3367 | No | - | - | - |
| 2 | Grok3 | 0.3197 | No | - | - | - |
| 3 | SD3.5 Large | 0.2363 | No | - | - | - |
| 4 | PixArt-Sigma | 0.2347 | No | PixArt-Σ: Weak-to-Strong Training of Diffusion T... | 2024-03-07 | Code |
| 5 | Infinity-2B | 0.2346 | No | Infinity-MM: Scaling Multimodal Performance with... | 2024-10-24 | Code |
| 6 | TextDiffuser2 | 0.2252 | No | TextDiffuser-2: Unleashing the Power of Language... | 2023-11-28 | - |
| 7 | Anytext | 0.2174 | No | AnyText: Multilingual Visual Text Generation And... | 2023-11-06 | Code |