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 426450 of 6689 papers

TitleStatusHype
IDE-3D: Interactive Disentangled Editing for High-Resolution 3D-aware Portrait SynthesisCode2
Gaussian Mixture Flow Matching ModelsCode2
Gen4Gen: Generative Data Pipeline for Generative Multi-Concept CompositionCode2
GANSpace: Discovering Interpretable GAN ControlsCode2
Learning Hazing to Dehazing: Towards Realistic Haze Generation for Real-World Image DehazingCode2
GAUDI: A Neural Architect for Immersive 3D Scene GenerationCode2
GenAI Arena: An Open Evaluation Platform for Generative ModelsCode2
GALIP: Generative Adversarial CLIPs for Text-to-Image SynthesisCode2
GAN Compression: Efficient Architectures for Interactive Conditional GANsCode2
From Parts to Whole: A Unified Reference Framework for Controllable Human Image GenerationCode2
ControlVideo: Training-free Controllable Text-to-Video GenerationCode2
From Text to Pose to Image: Improving Diffusion Model Control and QualityCode2
CharaConsist: Fine-Grained Consistent Character GenerationCode2
GAN Prior Embedded Network for Blind Face Restoration in the WildCode2
BDDM: Bilateral Denoising Diffusion Models for Fast and High-Quality Speech SynthesisCode2
BCI: Breast Cancer Immunohistochemical Image Generation through Pyramid Pix2pixCode2
ControlNet-XS: Rethinking the Control of Text-to-Image Diffusion Models as Feedback-Control SystemsCode2
Make It Count: Text-to-Image Generation with an Accurate Number of ObjectsCode2
Marrying Autoregressive Transformer and Diffusion with Multi-Reference AutoregressionCode2
Deep PCB To COCO ConvertorCode2
MasaCtrl: Tuning-Free Mutual Self-Attention Control for Consistent Image Synthesis and EditingCode2
Analyzing and Improving the Training Dynamics of Diffusion ModelsCode2
Bayesian Flow NetworksCode2
FouriScale: A Frequency Perspective on Training-Free High-Resolution Image SynthesisCode2
Beyond Self-attention: External Attention using Two Linear Layers for Visual TasksCode2
Show:102550
← PrevPage 18 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