List your company
ResearchFormerly WizWand

Text-to-Image Generation on COCO 256 x 256 2014 (val)

3.22FIDParti
1.929210.642119.35528.0679Sep 25, 2022Apr 8, 2023Oct 20, 2023May 2, 2024Nov 13, 2024May 27, 2025Dec 8, 2025
Updated 8mo ago

Evaluation results

MethodLinks
PartiType=Autoregressive, Training datasets=LAION (400M) + FIT (400M) + JFT (4B), #Params=20B + 630M (AE), Setting=Trained on external large dataset with access to MS-COCO, Finetuned on MS-COCO=true2022.093.22——
Re-Imagen+Type=Diffusion, Training datasets=KNN-ImageText (50M), #Params=2.5B + 750M (SR), Setting=Trained on external large dataset with access to MS-COCO2022.095.25——
U-ViT-S/2 (Deep)Type=Latent diffusion, Training datasets=MS-COCO (83K), #Params=58M + 123M (TE) + 84M (AE), Setting=Trained on MS-COCO2022.095.48——
U-ViT-S/2Type=Latent diffusion, Training datasets=MS-COCO (83K), #Params=45M + 123M (TE) + 84M (AE), Setting=Trained on MS-COCO2022.095.95——
Re-ImagenType=Diffusion, Training datasets=KNN-ImageText (50M), #Params=2.5B + 750M (SR), Setting=Zero-shot on external large dataset2022.096.88——
Re-ImagenType=Diffusion, Training datasets=KNN-ImageText (50M), #Params=2.5B + 750M (SR), Zero-shot=true2025.126.88——
FAE (DinoV2)+T5Type=Diffusion, Training datasets=CC12M, #Params=604M+ 514M (FAE), Zero-shot=true, Classifier-Free Guidance (CFG)=true2025.126.9——
FAE (SigLIPV2)+T5Type=Diffusion, Training datasets=CC12M, #Params=604M+ 514M (FAE), Zero-shot=true, Classifier-Free Guidance (CFG)=true2025.127.11——
PartiType=Autoregressive, Training datasets=LAION (400M) + FIT (400M) + JFT (4B), #Params=20B + 630M (AE), Setting=Zero-shot on external large dataset2022.097.23——
PartiType=Autoregressive, Training datasets=LAION (400M) + FIT (400M) + JFT (4B), #Params=20B + 630M (AE), Zero-shot=true2025.127.23——
ImagenType=Diffusion, Training datasets=Internal dataset (460M) + LAION (400M), #Params=2B + 4.6B (TE) + 600M (SR), Setting=Zero-shot on external large dataset2022.097.27——
ImagenType=Diffusion, Training datasets=Internal dataset (460M) + LAION (400M), #Params=2B + 4.6B (TE) + 600M (SR), Zero-shot=true2025.127.27——
U-Net*Type=Latent diffusion, Training datasets=MS-COCO (83K), #Params=53M + 123M (TE) + 84M (AE), Setting=Trained on MS-COCO, Retrieved from knowledge base=MS-COCO2022.097.32——
FAE (DinoV2)+T5Type=Diffusion, Training datasets=CC12M, #Params=604M+ 514M (FAE), Zero-shot=true, Classifier-Free Guidance (CFG)=false2025.127.47——
Make-A-SceneType=Autoregressive, Training datasets=Union datasets (with MS-COCO) (35M), #Params=4B, Setting=Trained on external large dataset with access to MS-COCO2022.097.55——
FAE (SigLIPV2)+T5Type=Diffusion, Training datasets=CC12M, #Params=604M+ 514M (FAE), Zero-shot=true, Classifier-Free Guidance (CFG)=false2025.127.57——
LAFITEType=GAN, Training datasets=MS-COCO (83K), #Params=75M + 151M (TE), Setting=Trained on MS-COCO2022.098.12——
FriroType=Diffusion, Training datasets=MS-COCO (83K), #Params=512M + 186M (TE) + 68M (AE), Setting=Trained on MS-COCO2022.098.97——
XMC-GANType=GAN, Training datasets=MS-COCO (83K), #Params=166M, Setting=Trained on MS-COCO2022.099.33——
DALL-E 2Type=Diffusion, Training datasets=DALL-E dataset (250M), #Params=4.5B + 700M (SR), Setting=Zero-shot on external large dataset2022.0910.39——
DALL-E 2Type=Diffusion, Training datasets=DALL-E dataset (250M), #Params=4.5B + 700M (SR), Zero-shot=true2025.1210.39——
Make-A-SceneType=Autoregressive, Training datasets=Union datasets (without MS-COCO) (35M), #Params=4B, Setting=Zero-shot on external large dataset2022.0911.84——
Make-A-SceneType=Autoregressive, Training datasets=Union datasets (without MS-COCO) (35M), #Params=4B, Zero-shot=true2025.1211.84——
GLIDEType=Diffusion, Training datasets=DALL-E dataset (250M), #Params=3.5B + 1.5B (SR), Setting=Zero-shot on external large dataset2022.0912.24——
GLIDEType=Diffusion, Training datasets=DALL-E dataset (250M), #Params=3.5B + 1.5B (SR), Zero-shot=true2025.1212.24——
VQ-Diffusion+Type=Discrete diffusion, Training datasets=Conceptual Caption Subset (7M), #Params=370M, Setting=Trained on external large dataset with access to MS-COCO2022.0913.86——
DF-GANType=GAN, Training datasets=MS-COCO (83K), #Params=19M, Setting=Trained on MS-COCO2022.0919.32——
VQ-DiffusionType=Discrete diffusion, Training datasets=MS-COCO (83K), #Params=370M, Setting=Trained on MS-COCO2022.0919.75——
SDVAE+T5Type=Diffusion, Training datasets=CC12M, #Params=604M, Zero-shot=true, Classifier-Free Guidance (CFG)=false2025.1221.25——
LAFITEType=GAN, Training datasets=CC3M (3M), #Params=75M + 151M (TE), Setting=Zero-shot on external large dataset2022.0926.94——
LAFITEType=GAN, Training datasets=CC3M (3M), #Params=75M + 151M (TE), Zero-shot=true2025.1226.94——
CogViewType=Autoregressive, Training datasets=Internal dataset (30M), #Params=4B, Setting=Zero-shot on external large dataset2022.0927.1——
CogViewType=Autoregressive, Training datasets=Internal dataset (30M), #Params=4B, Zero-shot=true2025.1227.1——
DALL-EType=Autoregressive, Training datasets=DALL-E dataset (250M), #Params=12B, Setting=Zero-shot on external large dataset2022.0928——
DALL-EType=Autoregressive, Training datasets=DALL-E dataset (250M), #Params=12B, Zero-shot=true2025.1228——
DM-GANType=GAN, Training datasets=MS-COCO (83K), #Params=46M, Setting=Trained on MS-COCO2022.0932.64——
AttnGANType=GAN, Training datasets=MS-COCO (83K), #Params=230M, Setting=Trained on MS-COCO2022.0935.49——
OriginalSource=Reference COCO Images2022.05—50—