Image Generation on TextAtlasEval
Metric: TextScenesHQ FID (lower is better)
Metric: TextScenesHQ FID (lower is better)
| # | Model↕ | TextScenesHQ FID▲ | Extra Data | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | SD3.5 Large | 64.44 | No | - | - | - |
| 2 | Infinity-2B | 71.59 | No | Infinity-MM: Scaling Multimodal Performance with... | 2024-10-24 | Code |
| 3 | PixArt-Sigma | 72.62 | No | PixArt-Σ: Weak-to-Strong Training of Diffusion T... | 2024-03-07 | Code |
| 4 | TextDiffuser2 | 84.1 | No | TextDiffuser-2: Unleashing the Power of Language... | 2023-11-28 | - |
| 5 | Dalle3 | 86.73 | No | - | - | - |
| 6 | Anytext | 101.32 | No | AnyText: Multilingual Visual Text Generation And... | 2023-11-06 | Code |