T2I-CompBench is a comprehensive benchmark for open-world compositional text-to-image generation, consisting of 6,000 compositional textual prompts from 3 categories (attribute binding, object relationships, and complex compositions) and 6 sub-categories (color binding, shape binding, texture binding, spatial relationships, non-spatial relationships, and complex compositions).
Variants: T2I-CompBench
This dataset is used in 1 benchmark:
| Task | Model | Paper | Date |
|---|---|---|---|
| Text-to-Image Generation | Emu3 | Emu3: Next-Token Prediction is All … | 2024-09-27 |
| Text-to-Image Generation | PixArt-a | PixArt-$α$: Fast Training of Diffusion … | 2023-09-30 |
Recent papers with results on this dataset: