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 1051–1100 of 6689 papers

TitleStatusHype
PersonaMagic: Stage-Regulated High-Fidelity Face Customization with Tandem EquilibriumCode1
Personalized Representation from Personalized GenerationCode2
BS-LDM: Effective Bone Suppression in High-Resolution Chest X-Ray Images with Conditional Latent Diffusion ModelsCode1
SemDP: Semantic-level Differential Privacy Protection for Face Datasets—0
SafeCFG: Redirecting Harmful Classifier-Free Guidance for Safe Generation—0
Semi-Supervised Adaptation of Diffusion Models for Handwritten Text Generation—0
Next Patch Prediction for Autoregressive Visual GenerationCode2
Qua^2SeDiMo: Quantifiable Quantization Sensitivity of Diffusion Models—0
DiffusionTrend: A Minimalist Approach to Virtual Fashion Try-On—0
LEDiff: Latent Exposure Diffusion for HDR Generation—0
Comparing noisy neural population dynamics using optimal transport distances—0
Tiled Diffusion—0
Enhancing Diffusion Models for High-Quality Image Generation—0
FlowAR: Scale-wise Autoregressive Image Generation Meets Flow MatchingCode2
LMFusion: Adapting Pretrained Language Models for Multimodal Generation—0
Flowing from Words to Pixels: A Framework for Cross-Modality Evolution—0
GALOT: Generative Active Learning via Optimizable Zero-shot Text-to-image Generation—0
Self-control: A Better Conditional Mechanism for Masked Autoregressive Model—0
Text2Relight: Creative Portrait Relighting with Text Guidance—0
Surrealistic-like Image Generation with Vision-Language ModelsCode0
Autoregressive Video Generation without Vector QuantizationCode4
FashionComposer: Compositional Fashion Image Generation—0
MMO-IG: Multi-Class and Multi-Scale Object Image Generation for Remote Sensing—0
E-CAR: Efficient Continuous Autoregressive Image Generation via Multistage Modeling—0
VideoDPO: Omni-Preference Alignment for Video Diffusion Generation—0
Posterior Mean Matching: Generative Modeling through Online Bayesian Inference—0
Numerical Pruning for Efficient Autoregressive Models—0
Guided and Variance-Corrected Fusion with One-shot Style Alignment for Large-Content Image GenerationCode0
ArtAug: Enhancing Text-to-Image Generation through Synthesis-Understanding InteractionCode0
3D MedDiffusion: A 3D Medical Diffusion Model for Controllable and High-quality Medical Image Generation—0
Prompt Augmentation for Self-supervised Text-guided Image Manipulation—0
Unsupervised Region-Based Image Editing of Denoising Diffusion Models—0
Stable Diffusion is a Natural Cross-Modal Decoder for Layered AI-generated Image Compression—0
Attentive Eraser: Unleashing Diffusion Model's Object Removal Potential via Self-Attention Redirection GuidanceCode3
F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration—0
Consistent Diffusion: Denoising Diffusion Model with Data-Consistent Training for Image Restoration—0
You Only Submit One Image to Find the Most Suitable Generative Model—0
OmniPrism: Learning Disentangled Visual Concept for Image Generation—0
Efficient Scaling of Diffusion Transformers for Text-to-Image Generation—0
Causal Diffusion Transformers for Generative ModelingCode2
IDProtector: An Adversarial Noise Encoder to Protect Against ID-Preserving Image GenerationCode1
VersaGen: Unleashing Versatile Visual Control for Text-to-Image SynthesisCode0
FedCAR: Cross-client Adaptive Re-weighting for Generative Models in Federated LearningCode0
LineArt: A Knowledge-guided Training-free High-quality Appearance Transfer for Design Drawing with Diffusion Model—0
A LoRA is Worth a Thousand Pictures—0
Relation-Guided Adversarial Learning for Data-free Knowledge TransferCode1
Nearly Zero-Cost Protection Against Mimicry by Personalized Diffusion Models—0
3D^2-Actor: Learning Pose-Conditioned 3D-Aware Denoiser for Realistic Gaussian Avatar ModelingCode1
Provably Secure Robust Image Steganography via Cross-Modal Error Correction—0
Grassmannian Geometry Meets Dynamic Mode Decomposition in DMD-GEN: A New Metric for Mode Collapse in Time Series Generative Models—0
Show:102550
← PrevPage 22 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