Image Generation

Description from the archive archive 2025-07-28; Papers-with-Code links inside it are rewritten to this site.

Benchmarks archive 2025-07-28

93 leaderboard tables shown for this task, 93 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted. 10 shown of 93 until expanded.

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

79 datasets whose archive record lists this task, ordered by the archive's paper count. 30 shown of 79 until expanded.

Subtasks archive 2025-07-28

23 subtasks in the archive's task tree.

Most implemented papers archive 2025-07-28

30 shown of 3,102 papers with code (6,689 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• Analyzing and Improving the Image Quality of StyleGAN
  3 Dec 2019 126 repositories listed Syntology ran 29 of 92 samples · 63 unverified · 18 pointer-only (licence)
  Overall, our improved model redefines the state of the art in unconditional image modeling, both in terms of existing distribution quality metrics as well as perceived image quality.
• Wasserstein GAN
  26 Jan 2017 120 repositories listed Syntology ran 13 of 22 samples · 9 unverified · 13 pointer-only (licence)
  We introduce a new algorithm named WGAN, an alternative to traditional GAN training.
• Progressive Growing of GANs for Improved Quality, Stability, and Variation
  27 Oct 2017 115 repositories listed Syntology ran 24 of 89 samples · 65 unverified · 19 pointer-only (licence)
  We describe a new training methodology for generative adversarial networks.
• Improved Training of Wasserstein GANs
  31 Mar 2017 110 repositories listed Syntology ran 27 of 49 samples · 22 unverified · 20 pointer-only (licence)
  Generative Adversarial Networks (GANs) are powerful generative models, but suffer from training instability.
• A Style-Based Generator Architecture for Generative Adversarial Networks
  12 Dec 2018 83 repositories listed Syntology ran 226 of 396 samples · 170 unverified · 229 pointer-only (licence)
  We propose an alternative generator architecture for generative adversarial networks, borrowing from style transfer literature.
• GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
  26 Jun 2017 71 repositories listed Syntology ran 3 of 4 samples · 1 unverified · 1 pointer-only (licence)
  Generative Adversarial Networks (GANs) excel at creating realistic images with complex models for which maximum likelihood is infeasible.
• Denoising Diffusion Probabilistic Models
  19 Jun 2020 70 repositories listed Syntology ran 178 of 253 samples · 75 unverified · 62 pointer-only (licence)
  We present high quality image synthesis results using diffusion probabilistic models, a class of latent variable models inspired by considerations from nonequilibrium thermodynamics.
• Self-Attention Generative Adversarial Networks
  21 May 2018 48 repositories listed Syntology ran 18 of 81 samples · 63 unverified · 1 pointer-only (licence)
  In this paper, we propose the Self-Attention Generative Adversarial Network (SAGAN) which allows attention-driven, long-range dependency modeling for image generation tasks.
• SinGAN: Learning a Generative Model from a Single Natural Image
  2 May 2019 47 repositories listed Syntology ran 2 of 11 samples · 9 unverified · 3 pointer-only (licence)
  We introduce SinGAN, an unconditional generative model that can be learned from a single natural image.
• Improved Techniques for Training GANs
  10 Jun 2016 46 repositories listed Syntology ran 1 of 2 samples · 1 unverified
  We present a variety of new architectural features and training procedures that we apply to the generative adversarial networks (GANs) framework.
• High-Resolution Image Synthesis with Latent Diffusion Models
  20 Dec 2021 41 repositories listed Syntology ran 19 of 28 samples · 9 unverified · 5 pointer-only (licence)
  By decomposing the image formation process into a sequential application of denoising autoencoders, diffusion models (DMs) achieve state-of-the-art synthesis results on image data and beyond.
• Generative Adversarial Text to Image Synthesis
  17 May 2016 39 repositories listed Syntology ran 9 of 19 samples · 10 unverified · 6 pointer-only (licence)
  Automatic synthesis of realistic images from text would be interesting and useful, but current AI systems are still far from this goal.
• Spectral Normalization for Generative Adversarial Networks
  16 Feb 2018 38 repositories listed Syntology ran 16 of 31 samples · 15 unverified · 14 pointer-only (licence)
  One of the challenges in the study of generative adversarial networks is the instability of its training.
• InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets
  12 Jun 2016 38 repositories listed Syntology ran 5 of 6 samples · 1 unverified
  This paper describes InfoGAN, an information-theoretic extension to the Generative Adversarial Network that is able to learn disentangled representations in a completely unsupervised manner.
• Conditional Image Synthesis With Auxiliary Classifier GANs
  30 Oct 2016 37 repositories listed Syntology ran 5 of 5 samples · 0 unverified · 5 pointer-only (licence)
  We expand on previous work for image quality assessment to provide two new analyses for assessing the discriminability and diversity of samples from class-conditional image synthesis models.
• Large Scale GAN Training for High Fidelity Natural Image Synthesis
  28 Sep 2018 35 repositories listed Syntology ran 14 of 41 samples · 27 unverified · 4 pointer-only (licence)
  Despite recent progress in generative image modeling, successfully generating high-resolution, diverse samples from complex datasets such as ImageNet remains an elusive goal.
• Density estimation using Real NVP
  27 May 2016 35 repositories listed Syntology ran 43 of 70 samples · 27 unverified · 33 pointer-only (licence)
  Unsupervised learning of probabilistic models is a central yet challenging problem in machine learning.
• Denoising Diffusion Implicit Models
  6 Oct 2020 29 repositories listed Syntology ran 28 of 50 samples · 22 unverified · 5 pointer-only (licence)
  Denoising diffusion probabilistic models (DDPMs) have achieved high quality image generation without adversarial training, yet they require simulating a Markov chain for many steps to produce a sample.
• Training Generative Adversarial Networks with Limited Data
  11 Jun 2020 28 repositories listed Syntology ran 5 of 29 samples · 24 unverified · 4 pointer-only (licence)
  We also find that the widely used CIFAR-10 is, in fact, a limited data benchmark, and improve the record FID from 5.
• Glow: Generative Flow with Invertible 1x1 Convolutions
  9 Jul 2018 27 repositories listed Syntology ran 75 of 129 samples · 54 unverified · 44 pointer-only (licence)
  Flow-based generative models (Dinh et al., 2014) are conceptually attractive due to tractability of the exact log-likelihood, tractability of exact latent-variable inference, and parallelizability of both training and…
• Semantic Image Synthesis with Spatially-Adaptive Normalization
  18 Mar 2019 24 repositories listed Syntology ran 5 of 9 samples · 4 unverified · 2 pointer-only (licence)
  Previous methods directly feed the semantic layout as input to the deep network, which is then processed through stacks of convolution, normalization, and nonlinearity layers.
• Adversarial Audio Synthesis
  12 Feb 2018 22 repositories listed Syntology ran 2 of 4 samples · 2 unverified · 4 pointer-only (licence)
  Audio signals are sampled at high temporal resolutions, and learning to synthesize audio requires capturing structure across a range of timescales.
• Instance Normalization: The Missing Ingredient for Fast Stylization
  27 Jul 2016 22 repositories listed Syntology ran 1 of 18 samples · 17 unverified
  It this paper we revisit the fast stylization method introduced in Ulyanov et.
• Diffusion Models Beat GANs on Image Synthesis
  11 May 2021 21 repositories listed Syntology ran 27 of 50 samples · 23 unverified · 16 pointer-only (licence)
  Finally, we find that classifier guidance combines well with upsampling diffusion models, further improving FID to 3.
• High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs
  30 Nov 2017 21 repositories listed Syntology ran 4 of 5 samples · 1 unverified · 3 pointer-only (licence)
  We present a new method for synthesizing high-resolution photo-realistic images from semantic label maps using conditional generative adversarial networks (conditional GANs).
• StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networks
  10 Dec 2016 21 repositories listed Syntology ran 11 of 31 samples · 20 unverified · 1 pointer-only (licence)
  Synthesizing high-quality images from text descriptions is a challenging problem in computer vision and has many practical applications.
• Elucidating the Design Space of Diffusion-Based Generative Models
  1 Jun 2022 20 repositories listed Syntology ran 11 of 21 samples · 10 unverified · 13 pointer-only (licence)
  We argue that the theory and practice of diffusion-based generative models are currently unnecessarily convoluted and seek to remedy the situation by presenting a design space that clearly separates the concrete design…
• AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networks
  28 Nov 2017 20 repositories listed Syntology ran 3 of 3 samples · 0 unverified
  In this paper, we propose an Attentional Generative Adversarial Network (AttnGAN) that allows attention-driven, multi-stage refinement for fine-grained text-to-image generation.
• Pixel Recurrent Neural Networks
  25 Jan 2016 20 repositories listed Syntology ran 19 of 29 samples · 10 unverified · 18 pointer-only (licence)
  Modeling the distribution of natural images is a landmark problem in unsupervised learning.
• DRAW: A Recurrent Neural Network For Image Generation
  16 Feb 2015 20 repositories listed Syntology ran 7 of 18 samples · 11 unverified · 9 pointer-only (licence)
  This paper introduces the Deep Recurrent Attentive Writer (DRAW) neural network architecture for image generation.

Syntology lines on 30 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. Read from the graph 2026-09-24.