Tasks
SotA
Datasets
Papers
Methods
Submit
About
SotA
/
Medical
/
Image Generation
/
ImageNet 64x64
Image Generation on ImageNet 64x64
Metric: Bits per dim (higher is better)
Leaderboard
Dataset
Loading chart...
Results
Submit a result
Export CSV
Sort:
Bits per dim (best first)
Bits per dim (worst first)
Date (newest first)
Date (oldest first)
Model name (A→Z)
#
Model
↕
Bits per dim
▼
Extra Data
Paper
Date
↕
Code
1
Logsparse (6 layers)
4.351
No
Enhancing the Locality and Breaking the Memory B...
2019-06-29
Code
2
Axial Transformer (6 layers)
4.032
No
Axial Attention in Multidimensional Transformers
2019-12-20
Code
3
Glow (Kingma and Dhariwal, 2018)
3.81
No
Glow: Generative Flow with Invertible 1x1 Convol...
2018-07-09
Code
4
Residual Flow
3.757
No
Residual Flows for Invertible Generative Modeling
2019-06-06
Code
5
MaCow (Unf)
3.75
No
MaCow: Masked Convolutional Generative Flow
2019-02-12
Code
6
Reformer (6 layers)
3.74
No
Reformer: The Efficient Transformer
2020-01-13
Code
7
Performer (6 layers)
3.719
No
Rethinking Attention with Performers
2020-09-30
Code
8
MALI
3.71
No
MALI: A memory efficient and reverse accurate in...
2021-02-09
Code
9
Reformer (12 layers)
3.71
No
Reformer: The Efficient Transformer
2020-01-13
Code
10
Parallel Multiscale
3.7
No
Parallel Multiscale Autoregressive Density Estim...
2017-03-10
-
11
Flow++
3.69
No
Flow++: Improving Flow-Based Generative Models w...
2019-02-01
Code
12
MaCow (Var)
3.69
No
MaCow: Masked Convolutional Generative Flow
2019-02-12
Code
13
Performer (12 layers)
3.636
No
Rethinking Attention with Performers
2020-09-30
Code
14
PixelCNN
3.57
No
PixelCNN Models with Auxiliary Variables for Nat...
2016-12-24
-
15
Gated PixelCNN (van den Oord et al., [2016c])
3.57
No
Conditional Image Generation with PixelCNN Decod...
2016-06-16
Code
16
Improved DDPM
3.53
No
Improved Denoising Diffusion Probabilistic Models
2021-02-18
Code
17
SPN
3.52
No
Generating High Fidelity Images with Subscale Pi...
2018-12-04
-
18
Very Deep VAE
3.52
No
Very Deep VAEs Generalize Autoregressive Models ...
2020-11-20
Code
19
Combiner-Mixture
3.504
No
Combiner: Full Attention Transformer with Sparse...
2021-07-12
Code
20
Sparse Transformer 59M (strided)
3.44
No
Generating Long Sequences with Sparse Transformers
2019-04-23
Code
21
MRCNF
3.44
No
Multi-Resolution Continuous Normalizing Flows
2021-06-15
Code
22
Hourglass
3.44
No
Hierarchical Transformers Are More Efficient Lan...
2021-10-26
Code
23
Routing Transformer
3.43
No
Efficient Content-Based Sparse Attention with Ro...
2020-03-12
Code
24
Combiner-Axial
3.42
No
Combiner: Full Attention Transformer with Sparse...
2021-07-12
Code
25
VDM
3.4
No
Variational Diffusion Models
2021-07-01
Code
26
NDM
3.35
No
Neural Diffusion Models
2023-10-12
-
27
FM
3.31
No
Flow Matching for Generative Modeling
2022-10-06
Code
28
BSI
3.22
No
Generative Modeling with Bayesian Sample Inference
2025-02-11
Code
29
NFDM
3.2
No
Neural Flow Diffusion Models: Learnable Forward ...
2024-04-19
Code
30
TarFlow
2.99
No
Normalizing Flows are Capable Generative Models
2024-12-09
Code
#1
Logsparse (6 layers)
SOTA
4.351
Bits per dim
· 2019-06-29
Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecasting
Code
#2
Axial Transformer (6 layers)
4.032
Bits per dim
· 2019-12-20
Axial Attention in Multidimensional Transformers
Code
#3
Glow (Kingma and Dhariwal, 2018)
SOTA
3.81
Bits per dim
· 2018-07-09
Glow: Generative Flow with Invertible 1x1 Convolutions
Code
#4
Residual Flow
3.757
Bits per dim
· 2019-06-06
Residual Flows for Invertible Generative Modeling
Code
#5
MaCow (Unf)
3.75
Bits per dim
· 2019-02-12
MaCow: Masked Convolutional Generative Flow
Code
#6
Reformer (6 layers)
3.74
Bits per dim
· 2020-01-13
Reformer: The Efficient Transformer
Code
#7
Performer (6 layers)
3.719
Bits per dim
· 2020-09-30
Rethinking Attention with Performers
Code
#8
MALI
3.71
Bits per dim
· 2021-02-09
MALI: A memory efficient and reverse accurate integrator for Neural ODEs
Code
#9
Reformer (12 layers)
3.71
Bits per dim
· 2020-01-13
Reformer: The Efficient Transformer
Code
#10
Parallel Multiscale
SOTA
3.7
Bits per dim
· 2017-03-10
Parallel Multiscale Autoregressive Density Estimation
#11
Flow++
3.69
Bits per dim
· 2019-02-01
Flow++: Improving Flow-Based Generative Models with Variational Dequantization and Architecture Design
Code
#12
MaCow (Var)
3.69
Bits per dim
· 2019-02-12
MaCow: Masked Convolutional Generative Flow
Code
#13
Performer (12 layers)
3.636
Bits per dim
· 2020-09-30
Rethinking Attention with Performers
Code
#14
PixelCNN
3.57
Bits per dim
· 2016-12-24
PixelCNN Models with Auxiliary Variables for Natural Image Modeling
#15
Gated PixelCNN (van den Oord et al., [2016c])
SOTA
3.57
Bits per dim
· 2016-06-16
Conditional Image Generation with PixelCNN Decoders
Code
#16
Improved DDPM
3.53
Bits per dim
· 2021-02-18
Improved Denoising Diffusion Probabilistic Models
Code
#17
SPN
3.52
Bits per dim
· 2018-12-04
Generating High Fidelity Images with Subscale Pixel Networks and Multidimensional Upscaling
#18
Very Deep VAE
3.52
Bits per dim
· 2020-11-20
Very Deep VAEs Generalize Autoregressive Models and Can Outperform Them on Images
Code
#19
Combiner-Mixture
3.504
Bits per dim
· 2021-07-12
Combiner: Full Attention Transformer with Sparse Computation Cost
Code
#20
Sparse Transformer 59M (strided)
3.44
Bits per dim
· 2019-04-23
Generating Long Sequences with Sparse Transformers
Code
#21
MRCNF
3.44
Bits per dim
· 2021-06-15
Multi-Resolution Continuous Normalizing Flows
Code
#22
Hourglass
3.44
Bits per dim
· 2021-10-26
Hierarchical Transformers Are More Efficient Language Models
Code
#23
Routing Transformer
3.43
Bits per dim
· 2020-03-12
Efficient Content-Based Sparse Attention with Routing Transformers
Code
#24
Combiner-Axial
3.42
Bits per dim
· 2021-07-12
Combiner: Full Attention Transformer with Sparse Computation Cost
Code
#25
VDM
3.4
Bits per dim
· 2021-07-01
Variational Diffusion Models
Code
#26
NDM
3.35
Bits per dim
· 2023-10-12
Neural Diffusion Models
#27
FM
3.31
Bits per dim
· 2022-10-06
Flow Matching for Generative Modeling
Code
#28
BSI
3.22
Bits per dim
· 2025-02-11
Generative Modeling with Bayesian Sample Inference
Code
#29
NFDM
3.2
Bits per dim
· 2024-04-19
Neural Flow Diffusion Models: Learnable Forward Process for Improved Diffusion Modelling
Code
#30
TarFlow
2.99
Bits per dim
· 2024-12-09
Normalizing Flows are Capable Generative Models
Code