List your company

Text-to-Image Generation on MS-COCO 30K (test)

4.88FIDCM3Leon-7B
1.601623.730845.8667.9892Sep 5, 2023Nov 20, 2023Feb 5, 2024Apr 22, 2024Jul 8, 2024Sep 23, 2024Dec 9, 2024

Evaluation results

MethodLinks
CM3Leon-7BRetrieval in Training=true, Responsible=true, Number of Retrieved Documents=2, Dataset Size=340M, Model Size=7B, Zero-shot=true, Samples per query=8, Selection=CLIP-based re-ranking2023.094.88—
RE-IMAGENRetrieval in Training=true, Responsible=false, Number of Retrieved Documents=2, Dataset Size=150M, Model Size=3.6B, Zero-shot=true2023.095.25—
CM3Leon-7BRetrieval in Training=true, Responsible=true, Number of Retrieved Documents=1, Dataset Size=340M, Model Size=7B, Zero-shot=true, Samples per query=8, Selection=CLIP-based re-ranking2023.095.78—
CM3Leon-760MRetrieval in Training=true, Responsible=true, Number of Retrieved Documents=2, Dataset Size=340M, Model Size=760M, Zero-shot=true, Samples per query=8, Selection=CLIP-based re-ranking2023.096.61—
ImagenType=Gen. Only, Params=3B, Images=5000M+2024.106.61—
PARTIRetrieval in Training=false, Responsible=false, Dataset Size=5B, Model Size=20B, Zero-shot=true2023.097.23—
MUSERetrieval in Training=false, Responsible=false, Dataset Size=500M, Model Size=3B, Zero-shot=true2023.097.88—
DreamLLMType=Und. and Gen. w/ pre-trained Diff., Params=7B, Images=N/A2024.108.76—
Show-oType=Joint Prob. Models, Params=1.3B, Images=35M2024.109.24—
UniDiffuserParam=0.9B2024.129.7130.93
DALL-E2Type=Gen. Only, Params=6.5B, Images=650M2024.1010.39—
CM3Leon-7BRetrieval in Training=true, Responsible=true, Number of Retrieved Documents=0, Dataset Size=340M, Model Size=7B, Zero-shot=true, Samples per query=8, Selection=CLIP-based re-ranking2023.0910.82—
SDv1.5Param=0.9B2024.1211.1230.63
CoDiParam=4.3B2024.1211.2630.69
CODIType=Und. and Gen. w/ pre-trained Diff., Params=400M, Images=N/A2024.1011.26—
KNN-DiffusionRetrieval in Training=false, Responsible=false, Number of Retrieved Documents=10, Dataset Size=70M, Model Size=400M, Zero-shot=true2023.0912.5—
Stable DiffusionRetrieval in Training=false, Responsible=false, Number of Retrieved Documents=0, Dataset Size=400M, Model Size=800M, Zero-shot=true2023.0912.6—
LDMType=Gen. Only, Params=1.4B, Images=400M2024.1012.64—
SEED-XType=Und. and Gen. w/ pre-trained Diff., Params=17B, Images=N/A2024.1012.68—
UIO-2XXLParam=6.8B2024.1213.39—
OmniFlowParam=3.4B, Pretraining with high quality data=true2024.1213.431.54
CM3Leon-350MRetrieval in Training=true, Responsible=true, Number of Retrieved Documents=2, Dataset Size=340M, Model Size=350M, Zero-shot=true, Samples per query=8, Selection=CLIP-based re-ranking2023.0914.2—
RA-CM3Retrieval in Training=true, Responsible=false, Number of Retrieved Documents=2, Dataset Size=150M, Model Size=2.7B, Zero-shot=true2023.0915.7—
SDXLParam=2.6B, Pretraining with high quality data=true2024.1216.4931.36
TransfusionType=Joint Prob. Models, Params=7B, Images=N/A2024.1016.8—
SingDiffusionBase Model=SD-2.0-base, Classifier Guidance=None2024.0318.0128.23
CCMBase Model=SDXL2024.1220.4731.73
SD3-MediumParam=2B, Pretraining with high quality data=true2024.1220.9430.65
SingDiffusionBase Model=SD-1.5, Classifier Guidance=None2024.0321.0927.71
PCMBase Model=SDXL2024.1221.1531.63
CCMBase Model=SD32024.1221.4931.41
MMAR-7BType=Joint Prob. Models, Params=7B, Images=145.2M2024.1022.9—
Stable Diffusion 2.0-baseBase Model=SD-2.0-base, Classifier Guidance=None2024.0325.1727.48
LCMBase Model=SD32024.1225.4431.27
DALL-EType=Gen. Only, Params=12B, Images=250M2024.1027.5—
PCMBase Model=SD32024.1228.5231.06
ChanmeleonType=Joint Prob. Models, Params=7B, Images=N/A2024.1029.6—
Hyper-SDBase Model=SDXL2024.1230.8731.3
Stable Diffusion 1.5Base Model=SD-1.5, Classifier Guidance=None2024.0331.8626.7
MMAR-0.5BType=Joint Prob. Models, Params=0.5B, Images=145.2M2024.1036.6—
OriginalBase Model=SD32024.1286.8426.18