Image Generation on TextAtlasEval

Metric: TextVisionBlend FID (lower is better)

LeaderboardDataset

Loading chart...

Results

Submit a result

Sort:

#	Model↕	TextVisionBlend FID▲	Extra Data	Paper	Date↕	Code
1	PixArt-Sigma	81.29	No	PixArt-Σ: Weak-to-Strong Training of Diffusion T...	2024-03-07	Code
2	Infinity-2B	95.69	No	Infinity-MM: Scaling Multimodal Performance with...	2024-10-24	Code
3	SD3.5 Large	118.85	No	-	-	-
4	Dalle3	153.21	No	-	-	-

#1PixArt-SigmaSOTA
81.29
TextVisionBlend FID· 2024-03-07
PixArt-Σ: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation Code
#2Infinity-2B
95.69
TextVisionBlend FID· 2024-10-24
Infinity-MM: Scaling Multimodal Performance with Large-Scale and High-Quality Instruction Data Code
#3SD3.5 Large
118.85
TextVisionBlend FID
No paper
#4Dalle3
153.21
TextVisionBlend FID
No paper