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 1451–1475 of 6689 papers

TitleStatusHype
SyreaNet: A Physically Guided Underwater Image Enhancement Framework Integrating Synthetic and Real ImagesCode1
DiffFaceSketch: High-Fidelity Face Image Synthesis with Sketch-Guided Latent Diffusion ModelCode1
Preconditioned Score-based Generative ModelsCode1
Robot Synesthesia: A Sound and Emotion Guided AI PainterCode1
Is This Loss Informative? Faster Text-to-Image Customization by Tracking Objective DynamicsCode1
Mask Conditional Synthetic Satellite ImageryCode1
Fair Diffusion: Instructing Text-to-Image Generation Models on FairnessCode1
Diversity is Definitely Needed: Improving Model-Agnostic Zero-shot Classification via Stable DiffusionCode1
Med-NCA: Robust and Lightweight Segmentation with Neural Cellular AutomataCode1
Information-Theoretic DiffusionCode1
KDEformer: Accelerating Transformers via Kernel Density EstimationCode1
ReDi: Efficient Learning-Free Diffusion Inference via Trajectory RetrievalCode1
Are Diffusion Models Vulnerable to Membership Inference Attacks?Code1
GANalyzer: Analysis and Manipulation of GANs Latent Space for Controllable Face SynthesisCode1
Stable Target Field for Reduced Variance Score Estimation in Diffusion ModelsCode1
PADL: Language-Directed Physics-Based Character ControlCode1
SAN: Inducing Metrizability of GAN with Discriminative Normalized Linear LayerCode1
Accelerating Guided Diffusion Sampling with Splitting Numerical MethodsCode1
Input Perturbation Reduces Exposure Bias in Diffusion ModelsCode1
Discovering and Mitigating Visual Biases through Keyword ExplanationCode1
Ultra-NeRF: Neural Radiance Fields for Ultrasound ImagingCode1
Fast Inference in Denoising Diffusion Models via MMD FinetuningCode1
Street-View Image Generation from a Bird's-Eye View LayoutCode1
Foreground-Background Separation through Concept Distillation from Generative Image Foundation ModelsCode1
Re-GAN: Data-Efficient GANs Training via Architectural ReconfigurationCode1
Show:102550
← PrevPage 59 of 268Next →
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