List your company

Text-to-Image Generation on COCO 30k subset 2014 (val)

2.47FIDRandom Train Images
1.46888.226914.98521.7431Nov 23, 2022Feb 22, 2023May 24, 2023Aug 23, 2023Nov 22, 2023Feb 21, 2024May 23, 2024

Evaluation results

MethodLinks
Random Train ImagesSetting=fine-tuned2022.112.47—
PartiSetting=fine-tuned2022.113.22—
ReCoSetting=fine-tuned, Guidance Scale=1.52022.115.18—
ReCo position WordSetting=fine-tuned, Guidance Scale=1.52022.115.98—
Retrieval BaselineSetting=fine-tuned2022.116.82—
eDiff-IResolution=256x256, Category=Proprietary Technologies2023.106.95—
eDiff-IResolution=256, Latency=32.0s, Family=Original, unaccelerated2024.056.95—
ReCo Image Descr.Setting=fine-tuned, Guidance Scale=1.52022.116.98—
SDv1.5Resolution=512, Latency=10.25s, Family=Teacher, Steps=200, Sampler=SDE, cfg=22024.057.21—
ImagenResolution=256x256, Category=Proprietary Technologies2023.107.27—
ImagenResolution=256, Latency=9.1s, Family=Original, unaccelerated2024.057.27—
Make-A-SceneSetting=fine-tuned2022.117.55—
KandinskyResolution=256x256, Category=Open Sourced Technologies2023.108.03—
Parti-3BResolution=256, Latency=6.4s, Family=Original, unaccelerated2024.058.1—
LAFITESetting=fine-tuned2022.118.12—
DMD2Resolution=512, Latency=0.09s, Family=Accelerated diffusion2024.058.35—
Stable Diffusion 2.1Resolution=256x256, Category=Open Sourced Technologies2023.108.59—
SDv1.5Resolution=512, Latency=2.59s, Family=Teacher, Steps=50, Sampler=ODE, cfg=32024.058.59—
GigaGANResolution=256x256, Category=Proprietary Technologies2023.109.09—
GigaGANResolution=512, Latency=0.13s, Family=GANs2024.059.09—
XMC-GANSetting=fine-tuned2022.119.33—
SLAM (4 step)Resolution=512, Latency=0.19s, Family=Accelerated diffusion2024.0510.06—
DALL-E 2Resolution=256x256, Category=Proprietary Technologies2023.1010.39—
DALL·E 2Resolution=256, Family=Original, unaccelerated2024.0510.39—
Parti-750MResolution=256, Family=Original, unaccelerated2024.0510.71—
DMDResolution=512, Latency=0.09s, Family=Accelerated diffusion2024.0511.49—
Make-A-SceneResolution=256, Latency=25.0s, Family=Original, unaccelerated2024.0511.84—
GLIDEResolution=256x256, Category=Open Sourced Technologies2023.1012.24—
GLIDEResolution=256, Latency=15.0s, Family=Original, unaccelerated2024.0512.24—
LDMResolution=256, Latency=3.7s, Family=Original, unaccelerated2024.0512.63—
UFOGenResolution=512, Latency=0.09s, Family=Accelerated diffusion2024.0512.78—
InstaFlow-0.9BResolution=512, Latency=0.09s, Family=Accelerated diffusion2024.0513.1—
StyleGAN-TResolution=512, Latency=0.10s, Family=GANs2024.0513.9—
HiPAResolution=512, Latency=0.09s, Family=Accelerated diffusion2024.0513.91—
IF*Resolution=256x256, Category=Open Sourced Technologies2023.1015.1—
Kandinsky 1.0Resolution=256x256, Category=Open Sourced Technologies2023.1015.4—
SwiftBrushResolution=512, Latency=0.09s, Family=Accelerated diffusion2024.0516.67—
CogView2Setting=fine-tuned2022.1117.7—
DALL-EResolution=256x256, Category=Proprietary Technologies2023.1017.89—
UniPC (4 step)Resolution=512, Latency=0.26s, Family=Accelerated diffusion2024.0519.57—
ruDALL-E MalevichResolution=256x256, Category=Open Sourced Technologies2023.1020—
GLIGENResolution=256x256, Category=Open Sourced Technologies2023.1021.04—
DPM++ (4 step)Resolution=512, Latency=0.26s, Family=Accelerated diffusion2024.0522.36—
LCM-LoRA (4 step)Resolution=512, Latency=0.19s, Family=Accelerated diffusion2024.0523.62—
LAFITEResolution=256, Latency=0.02s, Family=GANs2024.0526.94—
DALL·EResolution=256, Family=Original, unaccelerated2024.0527.5—
DALLEType=AR, Number of Parameters=12B2023.11—27.5
DALLE 2Type=Diff, Number of Parameters=5.5B2023.11—10.39
eDiff-IType=Diff, Inference Time (s)=32, Number of Parameters=9B2023.11—6.95
GigaGANType=GAN, Inference Time (s)=0.13, Number of Parameters=1B2023.11—9.09
GLIDEType=Diff, Inference Time (s)=15, Number of Parameters=5B2023.11—12.24
ImagenType=Diff, Inference Time (s)=9.1, Number of Parameters=3B2023.11—7.27
InstaFlowInference Time (s)=0.09, Number of Parameters=0.9B2023.11—13.1
LAFITEType=GAN, Inference Time (s)=0.02, Number of Parameters=75M2023.11—26.94
Make-A-SceneType=AR, Inference Time (s)=252023.11—11.84
Muse-3BInference Time (s)=1.3, Number of Parameters=3B2023.11—7.88
Parti-20BType=AR, Number of Parameters=20B2023.11—7.23
Stable DiffusionType=Diff, Inference Time (s)=2.9, Number of Parameters=0.9B2023.11—9.62
StyleGAN-TType=GAN, Inference Time (s)=0.1, Number of Parameters=1B2023.11—13.9
UFOGenInference Time (s)=0.09, Number of Parameters=0.9B2023.11—12.78