HyperAI
HyperAI
Home
Console
Docs
News
Papers
Tutorials
Datasets
Wiki
SOTA
LLM Models
GPU Leaderboard
Events
Search
About
Terms of Service
Privacy Policy
English
HyperAI
HyperAI
Toggle Sidebar
Search the site…
⌘
K
Command Palette
Search for a command to run...
Console
Home
SOTA
Image Generation
Image Generation On Ffhq 256 X 256
Image Generation On Ffhq 256 X 256
Metrics
FID
Results
Performance results of various models on this benchmark
Columns
Model Name
FID
Paper Title
Efficient-VDVAE
34.88
Efficient-VDVAE: Less is more
Efficient-vdVAE (Exposing)
34.88
Exposing flaws of generative model evaluation metrics and their unfair treatment of diffusion models
VE (erel=0.01)
15.67
Gotta Go Fast When Generating Data with Score-Based Models
VE (erel=0.02)
15.67
Gotta Go Fast When Generating Data with Score-Based Models
BigGAN
11.48
A U-Net Based Discriminator for Generative Adversarial Networks
VQGAN+Transformer
9.6
Taming Transformers for High-Resolution Image Synthesis
Unleash-Trans (Exposing)
9.02
Exposing flaws of generative model evaluation metrics and their unfair treatment of diffusion models
LDM
8.11
-
LDM (Exposing)
8.11
Exposing flaws of generative model evaluation metrics and their unfair treatment of diffusion models
GANFormer2
7.77
Compositional Transformers for Scene Generation
U-Net GAN
7.48
A U-Net Based Discriminator for Generative Adversarial Networks
GANFormer
7.42
Generative Adversarial Transformers
Unleashing Transformers
6.11
Unleashing Transformers: Parallel Token Prediction with Discrete Absorbing Diffusion for Fast High-Resolution Image Generation from Vector-Quantized Codes
UDM (RVE) + ST
5.54
Soft Truncation: A Universal Training Technique of Score-based Diffusion Model for High Precision Score Estimation
StyleGAN2-ada (Exposing)
5.30
Exposing flaws of generative model evaluation metrics and their unfair treatment of diffusion models
SWAGAN-Bi
5.22
SWAGAN: A Style-based Wavelet-driven Generative Model
INR-GAN-bil
4.95
Adversarial Generation of Continuous Images
LFM
4.55
Flow Matching in Latent Space
CIPS
4.38
Image Generators with Conditionally-Independent Pixel Synthesis
Projected-GAN (Exposing)
4.29
Exposing flaws of generative model evaluation metrics and their unfair treatment of diffusion models
0 of 51 row(s) selected.
Previous
Next
HyperAI
HyperAI
Home
Console
Docs
News
Papers
Tutorials
Datasets
Wiki
SOTA
LLM Models
GPU Leaderboard
Events
Search
About
Terms of Service
Privacy Policy
English
HyperAI
HyperAI
Toggle Sidebar
Search the site…
⌘
K
Command Palette
Search for a command to run...
Console
Home
SOTA
Image Generation
Image Generation On Ffhq 256 X 256
Image Generation On Ffhq 256 X 256
Metrics
FID
Results
Performance results of various models on this benchmark
Columns
Model Name
FID
Paper Title
Efficient-VDVAE
34.88
Efficient-VDVAE: Less is more
Efficient-vdVAE (Exposing)
34.88
Exposing flaws of generative model evaluation metrics and their unfair treatment of diffusion models
VE (erel=0.01)
15.67
Gotta Go Fast When Generating Data with Score-Based Models
VE (erel=0.02)
15.67
Gotta Go Fast When Generating Data with Score-Based Models
BigGAN
11.48
A U-Net Based Discriminator for Generative Adversarial Networks
VQGAN+Transformer
9.6
Taming Transformers for High-Resolution Image Synthesis
Unleash-Trans (Exposing)
9.02
Exposing flaws of generative model evaluation metrics and their unfair treatment of diffusion models
LDM
8.11
-
LDM (Exposing)
8.11
Exposing flaws of generative model evaluation metrics and their unfair treatment of diffusion models
GANFormer2
7.77
Compositional Transformers for Scene Generation
U-Net GAN
7.48
A U-Net Based Discriminator for Generative Adversarial Networks
GANFormer
7.42
Generative Adversarial Transformers
Unleashing Transformers
6.11
Unleashing Transformers: Parallel Token Prediction with Discrete Absorbing Diffusion for Fast High-Resolution Image Generation from Vector-Quantized Codes
UDM (RVE) + ST
5.54
Soft Truncation: A Universal Training Technique of Score-based Diffusion Model for High Precision Score Estimation
StyleGAN2-ada (Exposing)
5.30
Exposing flaws of generative model evaluation metrics and their unfair treatment of diffusion models
SWAGAN-Bi
5.22
SWAGAN: A Style-based Wavelet-driven Generative Model
INR-GAN-bil
4.95
Adversarial Generation of Continuous Images
LFM
4.55
Flow Matching in Latent Space
CIPS
4.38
Image Generators with Conditionally-Independent Pixel Synthesis
Projected-GAN (Exposing)
4.29
Exposing flaws of generative model evaluation metrics and their unfair treatment of diffusion models
0 of 51 row(s) selected.
Previous
Next
Image Generation On Ffhq 256 X 256 | SOTA | HyperAI