SOTAVerified

Image Generation

Image Generation (synthesis) is the task of generating new images from an existing dataset.

  • Unconditional generation refers to generating samples unconditionally from the dataset, i.e. $p(y)$
  • Conditional image generation (subtask) refers to generating samples conditionally from the dataset, based on a label, i.e. $p(y|x)$.

In this section, you can find state-of-the-art leaderboards for unconditional generation. For conditional generation, and other types of image generations, refer to the subtasks.

( Image credit: StyleGAN )

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 4251–4300 of 6689 papers

TitleStatusHype
Layer- and Timestep-Adaptive Differentiable Token Compression Ratios for Efficient Diffusion Transformers—0
LayerDiff: Exploring Text-guided Multi-layered Composable Image Synthesis via Layer-Collaborative Diffusion Model—0
Layered Diffusion Model for One-Shot High Resolution Text-to-Image Synthesis—0
LayerFusion: Harmonized Multi-Layer Text-to-Image Generation with Generative Priors—0
LayeringDiff: Layered Image Synthesis via Generation, then Disassembly with Generative Knowledge—0
Layer Separation: Adjustable Joint Space Width Images Synthesis in Conventional Radiography—0
A Generic Shared Attention Mechanism for Various Backbone Neural Networks—0
Layout-and-Retouch: A Dual-stage Framework for Improving Diversity in Personalized Image Generation—0
Layout-Bridging Text-to-Image Synthesis—0
Layout Control and Semantic Guidance with Attention Loss Backward for T2I Diffusion Model—0
LayoutDiffuse: Adapting Foundational Diffusion Models for Layout-to-Image Generation—0
Assessing a Single Image in Reference-Guided Image Synthesis—0
Towards Understanding and Quantifying Uncertainty for Text-to-Image Generation—0
Layout-to-Image Generation with Localized Descriptions using ControlNet with Cross-Attention Control—0
LayoutTransformer: Relation-Aware Scene Layout Generation—0
Lay-Your-Scene: Natural Scene Layout Generation with Diffusion Transformers—0
A spatiotemporal style transfer algorithm for dynamic visual stimulus generation—0
LDC-VAE: A Latent Distribution Consistency Approach to Variational AutoEncoders—0
LDEdit: Towards Generalized Text Guided Image Manipulation via Latent Diffusion Models—0
LDGen: Enhancing Text-to-Image Synthesis via Large Language Model-Driven Language Representation—0
LD-Pruner: Efficient Pruning of Latent Diffusion Models using Task-Agnostic Insights—0
Lean Attention: Hardware-Aware Scalable Attention Mechanism for the Decode-Phase of Transformers—0
Towards Understanding Cross and Self-Attention in Stable Diffusion for Text-Guided Image Editing—0
Learning 3D-aware Image Synthesis with Unknown Pose Distribution—0
Learning 3D Robotics Perception using Inductive Priors—0
Accurate generation of stochastic dynamics based on multi-model Generative Adversarial Networks—0
Learning AND-OR Templates for Professional Photograph Parsing and Guidance—0
One-to-one Mapping for Unpaired Image-to-image Translation—0
Towards Understanding the Generative Capability of Adversarially Robust Classifiers—0
Learning Compact Recurrent Neural Networks with Block-Term Tensor Decomposition—0
Learning Compositional Visual Concepts with Mutual Consistency—0
Control3Diff: Learning Controllable 3D Diffusion Models from Single-view Images—0
Learning Coupled Dictionaries from Unpaired Data for Image Super-Resolution—0
Learning Detailed Radiance Manifolds for High-Fidelity and 3D-Consistent Portrait Synthesis from Monocular Image—0
Private Gradient Estimation is Useful for Generative Modeling—0
Learning Diffusion Texture Priors for Image Restoration—0
Learning Disentangled Identifiers for Action-Customized Text-to-Image Generation—0
Towards Understanding the Mechanisms of Classifier-Free Guidance—0
Learning Disentangled Representations with Reference-Based Variational Autoencoders—0
Learning Dynamic Style Kernels for Artistic Style Transfer—0
Diffusion Models for Accurate Channel Distribution Generation—0
Learning Energy-Based Generative Models via Coarse-to-Fine Expanding and Sampling—0
Learning Energy-based Model via Dual-MCMC Teaching—0
Learning Fast Samplers for Diffusion Models by Differentiating Through Sample Quality—0
Wavelets Are All You Need for Autoregressive Image Generation—0
A Simple Background Augmentation Method for Object Detection with Diffusion Model—0
Learning from THEODORE: A Synthetic Omnidirectional Top-View Indoor Dataset for Deep Transfer Learning—0
Learning Generative Models with Goal-conditioned Reinforcement Learning—0
Learning geometry-image representation for 3D point cloud generation—0
A Simple Approach to Unifying Diffusion-based Conditional Generation—0
Show:102550
← PrevPage 86 of 134Next →
All datasetsImageNet 256x256CIFAR-10ImageNet 64x64ImageNet 512x512FFHQ 256 x 256CelebA 64x64ImageNet 32x32LSUN Bedroom 256 x 256STL-10LSUN Churches 256 x 256ImageNet 128x128FFHQ 1024 x 1024

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Improved DDPMFID12.3—Unverified
2ADMFID11.84—Unverified
3BigGAN-deepFID8.1—Unverified
4Polarity-BigGANFID6.82—Unverified
5VQGAN+Transformer (k=mixed, p=1.0, a=0.005)FID6.59—Unverified
6MaskGITFID6.18—Unverified
7VQGAN+Transformer (k=600, p=1.0, a=0.05)FID5.2—Unverified
8CDMFID4.88—Unverified
9ADM-GFID4.59—Unverified
10RINFID4.51—Unverified
#ModelMetricClaimedVerifiedStatus
1PresGANFID52.2—Unverified
2RESFLOWFID48.29—Unverified
3Residual FlowFID46.37—Unverified
4GLF+perceptual loss (ours)FID44.6—Unverified
5ProdPoly no activation functionsFID40.45—Unverified
6ProdPoly no activation functionsFID36.77—Unverified
7ACGANFID35.47—Unverified
8DenseFlow-74-10FID34.9—Unverified
9NVAE w/ flowFID32.53—Unverified
10QSNGANFID31.97—Unverified
#ModelMetricClaimedVerifiedStatus
1GLIDE + CLSFID30.87—Unverified
2GLIDE + CLIPFID30.46—Unverified
3GLIDE + CLS-FREEFID29.22—Unverified
4GLIDE + CLIP + CLS + CLS-FREEFID29.18—Unverified
5PGMGANFID21.73—Unverified
6CLR-GANFID20.27—Unverified
7FMFID14.45—Unverified
8CT (Direct Generation, NFE=1)FID13—Unverified
9CT (Direct Generation, NFE=2)FID11.1—Unverified
10GLIDE +CLSKID7.95—Unverified