List your company
ResearchFormerly WizWand

Text-to-Image Alignment on MS COCO

31.58CLIP ScoreAC
-0.947047.4974815.94224.38652Jan 7, 2026Feb 6, 2026Mar 8, 2026Apr 7, 2026May 7, 2026Jun 6, 2026Jul 7, 2026
Updated 3mo ago

Evaluation results

MethodLinks
AC2026.0131.58
SD v1.52026.0131.42
MACE2026.0131.05
SPM2026.0130.77
FMN2026.0130.56
ESD2026.0130.12
SalUn2026.0129.93
FIA2026.0129.56
UCE2026.0129.25
CP2026.0127.93
D2POSteps=7, Solver=iPNDM2026.0726.57
D2POSteps=6, Solver=iPNDM2026.0726.52
LD3Steps=7, Solver=iPNDM2026.0726.37
D2POSteps=5, Solver=iPNDM2026.0726.3
LD3Steps=6, Solver=iPNDM2026.0726.22
LD3Steps=5, Solver=iPNDM2026.0726.21
D2POSteps=4, Solver=iPNDM2026.0726.01
LD3Steps=4, Solver=iPNDM2026.0725.87
hub text identificationModel=apple/DFN5B-CLIP-ViT-H-14-378, Text Category=Hub text2026.041.023
GLSModel=apple/DFN5B-CLIP-ViT-H-14-378, Text Category=Hub text2026.040.995
hub text identificationModel=apple/DFN5B-CLIP-ViT-H-14, Text Category=Hub text2026.040.974
GLSModel=apple/DFN5B-CLIP-ViT-H-14, Text Category=Hub text2026.040.965
hub text identificationModel=openai/clip-vit-base-patch32, Text Category=Hub text2026.040.842
HumanModel=apple/DFN5B-CLIP-ViT-H-14, Text Category=Caption text2026.040.838
HumanModel=apple/DFN5B-CLIP-ViT-H-14-378, Text Category=Caption text2026.040.837
hub text identificationModel=laion/CLIP-ViT-H-14-laion2B-s32B-b79K, Text Category=Hub text2026.040.825
hub text identificationModel=apple/DFN2B-CLIP-ViT-L-14, Text Category=Hub text2026.040.814
BLIP-2Model=apple/DFN5B-CLIP-ViT-H-14, Text Category=Caption text2026.040.789
hub text identificationModel=laion/CLIP-ViT-L-14-laion2B-s32B-b82K, Text Category=Hub text2026.040.782
GLSModel=laion/CLIP-ViT-H-14-laion2B-s32B-b79K, Text Category=Hub text2026.040.78
BLIP-2Model=apple/DFN5B-CLIP-ViT-H-14-378, Text Category=Caption text2026.040.777
HumanModel=laion/CLIP-ViT-H-14-laion2B-s32B-b79K, Text Category=Caption text2026.040.771
GLSModel=laion/CLIP-ViT-g-14-laion2B-s12B-b42K, Text Category=Hub text2026.040.767
HumanModel=openai/clip-vit-base-patch32, Text Category=Caption text2026.040.759
HumanModel=laion/CLIP-ViT-L-14-laion2B-s32B-b82K, Text Category=Caption text2026.040.748
hub text identificationModel=laion/CLIP-ViT-g-14-laion2B-s12B-b42K, Text Category=Hub text2026.040.747
BLIP-2Model=openai/clip-vit-base-patch32, Text Category=Caption text2026.040.739
GLSModel=openai/clip-vit-base-patch32, Text Category=Hub text2026.040.732
BLIP-2Model=laion/CLIP-ViT-H-14-laion2B-s32B-b79K, Text Category=Caption text2026.040.729
GLSModel=apple/DFN2B-CLIP-ViT-L-14, Text Category=Hub text2026.040.723
HumanModel=apple/DFN2B-CLIP-ViT-L-14, Text Category=Caption text2026.040.722
HumanModel=laion/CLIP-ViT-g-14-laion2B-s12B-b42K, Text Category=Caption text2026.040.721
BLIP-2Model=laion/CLIP-ViT-L-14-laion2B-s32B-b82K, Text Category=Caption text2026.040.72
hub text identificationModel=openai/clip-vit-large-patch14-336, Text Category=Hub text2026.040.701
GLSModel=laion/CLIP-ViT-L-14-laion2B-s32B-b82K, Text Category=Hub text2026.040.69
BLIP-2Model=laion/CLIP-ViT-g-14-laion2B-s12B-b42K, Text Category=Caption text2026.040.688
BLIP-2Model=apple/DFN2B-CLIP-ViT-L-14, Text Category=Caption text2026.040.678
GLSModel=openai/clip-vit-large-patch14-336, Text Category=Hub text2026.040.677
HumanModel=openai/clip-vit-large-patch14-336, Text Category=Caption text2026.040.654
hub text identificationModel=openai/clip-vit-large-patch14, Text Category=Hub text2026.040.649
hub text identificationModel=BAAI/AltCLIP, Text Category=Hub text2026.040.643
HumanModel=openai/clip-vit-large-patch14, Text Category=Caption text2026.040.639
HumanModel=BAAI/AltCLIP, Text Category=Caption text2026.040.635
GLSModel=openai/clip-vit-large-patch14, Text Category=Hub text2026.040.633
BLIP-2Model=openai/clip-vit-large-patch14-336, Text Category=Caption text2026.040.628
BLIP-2Model=BAAI/AltCLIP, Text Category=Caption text2026.040.622
BLIP-2Model=openai/clip-vit-large-patch14, Text Category=Caption text2026.040.613
GLSModel=BAAI/AltCLIP, Text Category=Hub text2026.040.512
BaselineModel Version=SD v1.4, CLIP Backbone=ViT-B/322026.030.32
AFM-curveModel Version=SD v1.5, CLIP Backbone=ViT-B/322026.030.319
BaselineModel Version=SD v1.5, CLIP Backbone=ViT-B/322026.030.318
AFM-curveModel Version=SD v1.4, CLIP Backbone=ViT-B/322026.030.318
AFM-curve + entropyModel Version=SD v1.4, CLIP Backbone=ViT-B/322026.030.317
AFM-curve + entropyModel Version=SD v1.5, CLIP Backbone=ViT-B/322026.030.316
FreeUModel Version=SD v1.5, CLIP Backbone=ViT-B/322026.030.307
FreeUModel Version=SD v1.4, CLIP Backbone=ViT-B/322026.030.307
SAGModel Version=SD v1.5, CLIP Backbone=ViT-B/322026.030.305
SAGModel Version=SD v1.4, CLIP Backbone=ViT-B/322026.030.304