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

Showing 12511275 of 6689 papers

TitleStatusHype
AutoStory: Generating Diverse Storytelling Images with Minimal Human EffortCode1
DPImageBench: A Unified Benchmark for Differentially Private Image SynthesisCode1
Improving GANs for Long-Tailed Data through Group Spectral RegularizationCode1
Improved Training of Wasserstein GANsCode1
Domain-Adaptive 3D Medical Image Synthesis: An Efficient Unsupervised ApproachCode1
Improved Transformer for High-Resolution GANsCode1
DMM: Building a Versatile Image Generation Model via Distillation-Based Model MergingCode1
Cross-Attention Head Position Patterns Can Align with Human Visual Concepts in Text-to-Image Generative ModelsCode1
DocSynth: A Layout Guided Approach for Controllable Document Image SynthesisCode1
Do Neural Optimal Transport Solvers Work? A Continuous Wasserstein-2 BenchmarkCode1
Improving GAN Training with Probability Ratio Clipping and Sample ReweightingCode1
Improved Techniques for Maximum Likelihood Estimation for Diffusion ODEsCode1
Cross Attention Based Style Distribution for Controllable Person Image SynthesisCode1
Improved Techniques for Training Consistency ModelsCode1
Diversity-aware Channel Pruning for StyleGAN CompressionCode1
DM-GAN: Dynamic Memory Generative Adversarial Networks for Text-to-Image SynthesisCode1
Improved Precision and Recall Metric for Assessing Generative ModelsCode1
Cross-domain Correspondence Learning for Exemplar-based Image TranslationCode1
AutoSplice: A Text-prompt Manipulated Image Dataset for Media ForensicsCode1
Improved Techniques for Training GANsCode1
Cross Initialization for Personalized Text-to-Image GenerationCode1
CreativeSynth: Cross-Art-Attention for Artistic Image Synthesis with Multimodal DiffusionCode1
Diverse Semantic Image Synthesis via Probability Distribution ModelingCode1
Cross-Modal Contrastive Learning for Text-to-Image GenerationCode1
Diverse Image Synthesis from Semantic Layouts via Conditional IMLECode1
Show:102550
← PrevPage 51 of 268Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Improved DDPMFID12.3Unverified
2ADMFID11.84Unverified
3BigGAN-deepFID8.1Unverified
4Polarity-BigGANFID6.82Unverified
5VQGAN+Transformer (k=mixed, p=1.0, a=0.005)FID6.59Unverified
6MaskGITFID6.18Unverified
7VQGAN+Transformer (k=600, p=1.0, a=0.05)FID5.2Unverified
8CDMFID4.88Unverified
9ADM-GFID4.59Unverified
10RINFID4.51Unverified
#ModelMetricClaimedVerifiedStatus
1PresGANFID52.2Unverified
2RESFLOWFID48.29Unverified
3Residual FlowFID46.37Unverified
4GLF+perceptual loss (ours)FID44.6Unverified
5ProdPoly no activation functionsFID40.45Unverified
6ProdPoly no activation functionsFID36.77Unverified
7ACGANFID35.47Unverified
8DenseFlow-74-10FID34.9Unverified
9NVAE w/ flowFID32.53Unverified
10QSNGANFID31.97Unverified
#ModelMetricClaimedVerifiedStatus
1GLIDE + CLSFID30.87Unverified
2GLIDE + CLIPFID30.46Unverified
3GLIDE + CLS-FREEFID29.22Unverified
4GLIDE + CLIP + CLS + CLS-FREEFID29.18Unverified
5PGMGANFID21.73Unverified
6CLR-GANFID20.27Unverified
7FMFID14.45Unverified
8CT (Direct Generation, NFE=1)FID13Unverified
9CT (Direct Generation, NFE=2)FID11.1Unverified
10GLIDE +CLSKID7.95Unverified