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 5601–5650 of 6689 papers

TitleStatusHype
Effective Shortcut Technique for GAN—0
Effect of Instance Normalization on Fine-Grained Control for Sketch-Based Face Image Generation—0
Efficiency Meets Fidelity: A Novel Quantization Framework for Stable Diffusion—0
Efficient-3DiM: Learning a Generalizable Single-image Novel-view Synthesizer in One Day—0
Synthetic Lung X-ray Generation through Cross-Attention and Affinity Transformation—0
Efficient Cross-Lingual Transfer for Chinese Stable Diffusion with Images as Pivots—0
Block and Detail: Scaffolding Sketch-to-Image Generation—0
Synthetic Medical Imaging Generation with Generative Adversarial Networks For Plain Radiographs—0
Efficient Diffusion Training through Parallelization with Truncated Karhunen-Loève Expansion—0
Synthetic Privileged Information Enhances Medical Image Representation Learning—0
Synthetic Shifts to Initial Seed Vector Exposes the Brittle Nature of Latent-Based Diffusion Models—0
Efficient Exploration of Image Classifier Failures with Bayesian Optimization and Text-to-Image Models—0
Efficient Flow Matching using Latent Variables—0
Efficient Generative Modeling with Residual Vector Quantization-Based Tokens—0
Efficient Hair Style Transfer with Generative Adversarial Networks—0
Visual Indeterminacy in GAN Art—0
SynthRAD2025 Grand Challenge dataset: generating synthetic CTs for radiotherapy—0
Efficient Listener: Dyadic Facial Motion Synthesis via Action Diffusion—0
Efficient Multi-Instance Generation with Janus-Pro-Dirven Prompt Parsing—0
Visual Lexicon: Rich Image Features in Language Space—0
Efficient Pruning of Text-to-Image Models: Insights from Pruning Stable Diffusion—0
Efficient Quantization Strategies for Latent Diffusion Models—0
Semantically-Prompted Language Models Improve Visual Descriptions—0
Efficient Scaling of Diffusion Transformers for Text-to-Image Generation—0
Efficient training for future video generation based on hierarchical disentangled representation of latent variables—0
Efficient Training with Denoised Neural Weights—0
Efficient Transfer Learning in Diffusion Models via Adversarial Noise—0
Systematic Analysis of Image Generation using GANs—0
Efficient-VQGAN: Towards High-Resolution Image Generation with Efficient Vision Transformers—0
Systematic Review of Techniques in Brain Image Synthesis using Deep Learning—0
Enhancing CT Image synthesis from multi-modal MRI data based on a multi-task neural network framework—0
T2CI-GAN: Text to Compressed Image generation using Generative Adversarial Network—0
EIDT-V: Exploiting Intersections in Diffusion Trajectories for Model-Agnostic, Zero-Shot, Training-Free Text-to-Video Generation—0
Hierarchy Composition GAN for High-fidelity Image Synthesis—0
EINS: Long Short-Term Memory with Extrapolated Input Network Simplification—0
T2IAT: Measuring Valence and Stereotypical Biases in Text-to-Image Generation—0
ELBO-T2IAlign: A Generic ELBO-Based Method for Calibrating Pixel-level Text-Image Alignment in Diffusion Models—0
BlobGAN-3D: A Spatially-Disentangled 3D-Aware Generative Model for Indoor Scenes—0
BlobCtrl: A Unified and Flexible Framework for Element-level Image Generation and Editing—0
ELODIN: Naming Concepts in Embedding Spaces—0
Elucidating Flow Matching ODE Dynamics with Respect to Data Geometries—0
Adapting Text-to-Image Generation with Feature Difference Instruction for Generic Image Restoration—0
BLIP-Diffusion: Pre-trained Subject Representation for Controllable Text-to-Image Generation and Editing—0
T2I-FactualBench: Benchmarking the Factuality of Text-to-Image Models with Knowledge-Intensive Concepts—0
Visual Madlibs: Fill in the blank Image Generation and Question Answering—0
Emage: Non-Autoregressive Text-to-Image Generation—0
T2IW: Joint Text to Image & Watermark Generation—0
Emergence and Evolution of Interpretable Concepts in Diffusion Models—0
Blind Motion Deblurring through SinGAN Architecture—0
EM-GAN: Fast Stress Analysis for Multi-Segment Interconnect Using Generative Adversarial Networks—0
Show:102550
← PrevPage 113 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