Image Generation on TextAtlasEval

Metric: TextVisionBlend Clip Score (higher is better)

LeaderboardDataset

Loading chart...

Results

Sort:

#	Model↕	TextVisionBlend Clip Score▼	Extra Data	Paper	Date↕	Code
1	Infinity-2B	0.1979	No	Infinity-MM: Scaling Multimodal Performance with...	2024-10-24	Code
2	Dalle3	0.1938	No	-	-	-
3	PixArt-Sigma	0.1891	No	PixArt-Σ: Weak-to-Strong Training of Diffusion T...	2024-03-07	Code
4	SD3.5 Large	0.1846	No	-	-	-
5	Grok3	0.1697	No	-	-	-

#1Infinity-2BSOTA
0.1979
TextVisionBlend Clip Score· 2024-10-24
Infinity-MM: Scaling Multimodal Performance with Large-Scale and High-Quality Instruction Data Code
#2Dalle3
0.1938
TextVisionBlend Clip Score
No paper
#3PixArt-SigmaSOTA
0.1891
TextVisionBlend Clip Score· 2024-03-07
PixArt-Σ: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation Code
#4SD3.5 Large
0.1846
TextVisionBlend Clip Score
No paper
#5Grok3
0.1697
TextVisionBlend Clip Score
No paper