Text-to-Image Generation on ImageNet (Density, Coverage, VS, ClipScore, SPP) benchmark leaderboard · SOTA2 Research

Text-to-Image Generation on ImageNet (Density, Coverage, VS, ClipScore, SPP)

1.389DensityIG-NeurIPS’24

Evaluation Results

Method	Links
IG-NeurIPS’242026.02		1.389	0.627	27.415	0.31	0.129
CADS-ICLR’242026.02		1.374	0.636	28.456	0.309	0.133
GASS2026.02		1.164	0.611	28.877	0.313	0.141
Vanilla Guidance (CFG)2026.02		1.13	0.623	31.826	0.308	0.143
Vanilla Guidance (CFG)2026.02		1.105	0.588	28.119	0.308	0.137
SPELL-ICML’252026.02		1.105	0.585	28.433	0.302	0.128
PG-ICLR’242026.02		1.103	0.586	28.119	0.308	0.129
PG-ICLR’242026.02		1.039	0.614	32.082	0.309	0.146
GASS2026.02		1.015	0.603	32.711	0.309	0.149
SPELL-ICML’252026.02		0.912	0.578	32.601	0.305	0.144
IG-NeurIPS’242026.02		0.901	0.574	28.935	0.306	0.14
CADS-ICLR’242026.02		0.897	0.567	28.935	0.306	0.142