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 2201–2250 of 6689 papers

TitleStatusHype
RefDrop: Controllable Consistency in Image or Video Generation via Reference Feature Guidance—0
Glauber Generative Model: Discrete Diffusion Models via Binary Classification—0
The Poisson Midpoint Method for Langevin Dynamics: Provably Efficient Discretization for Diffusion Models—0
TIE: Revolutionizing Text-based Image Editing for Complex-Prompt Following and High-Fidelity Editing—0
Training-free Editioning of Text-to-Image Models—0
Anonymization Prompt Learning for Facial Privacy-Preserving Text-to-Image Generation—0
PromptFix: You Prompt and We Fix the PhotoCode4
Unified Editing of Panorama, 3D Scenes, and Videos Through Disentangled Self-Attention Injection—0
User-Friendly Customized Generation with Multi-Modal PromptsCode1
Automatic Jailbreaking of the Text-to-Image Generative AI SystemsCode1
Method and Software Tool for Generating Artificial Databases of Biomedical Images Based on Deep Neural Networks—0
Lateralization MLP: A Simple Brain-inspired Architecture for DiffusionCode0
Underwater Image Enhancement by Diffusion Model with Customized CLIP-ClassifierCode2
PTQ4DiT: Post-training Quantization for Diffusion TransformersCode1
Enhancing Consistency-Based Image Generation via Adversarialy-Trained Classification and Energy-Based DiscriminationCode0
Scaling Diffusion Mamba with Bidirectional SSMs for Efficient Image and Video Generation—0
SG-Adapter: Enhancing Text-to-Image Generation with Scene Graph Guidance—0
Learning to Discretize Denoising Diffusion ODEsCode1
ArtWeaver: Advanced Dynamic Style Integration via Diffusion Model—0
Defensive Unlearning with Adversarial Training for Robust Concept Erasure in Diffusion ModelsCode2
Unlearning Concepts in Diffusion Model via Concept Domain Correction and Concept Preserving GradientCode1
Time Cell Inspired Temporal Codebook in Spiking Neural Networks for Enhanced Image Generation—0
DLPO: Diffusion Model Loss-Guided Reinforcement Learning for Fine-Tuning Text-to-Speech Diffusion Models—0
Fast-DDPM: Fast Denoising Diffusion Probabilistic Models for Medical Image-to-Image GenerationCode2
RectifID: Personalizing Rectified Flow with Anchored Classifier GuidanceCode2
OpFlowTalker: Realistic and Natural Talking Face Generation via Optical Flow Guidance—0
PaGoDA: Progressive Growing of a One-Step Generator from a Low-Resolution Diffusion TeacherCode1
DiM: Diffusion Mamba for Efficient High-Resolution Image SynthesisCode3
LG-VQ: Language-Guided Codebook Learning—0
Rate-Adaptive Quantization: A Multi-Rate Codebook Adaptation for Vector Quantization-based Generative ModelsCode1
Diffusion models for Gaussian distributions: Exact solutions and Wasserstein errors—0
Improved Distribution Matching Distillation for Fast Image SynthesisCode5
LiteVAE: Lightweight and Efficient Variational Autoencoders for Latent Diffusion Models—0
FreeTuner: Any Subject in Any Style with Training-free Diffusion—0
Membership Inference on Text-to-Image Diffusion Models via Conditional Likelihood DiscrepancyCode1
Good Seed Makes a Good Crop: Discovering Secret Seeds in Text-to-Image Diffusion Models—0
TerDiT: Ternary Diffusion Models with TransformersCode2
Bracket Diffusion: HDR Image Generation by Consistent LDR Denoising—0
Conditional Diffusion on Web-Scale Image Pairs leads to Diverse Image Variations—0
Learning Multi-dimensional Human Preference for Text-to-Image GenerationCode7
The Disappearance of Timestep Embedding in Modern Time-Dependent Neural NetworksCode0
Visual Analysis of Prediction Uncertainty in Neural Networks for Deep Image Synthesis—0
Generalized Compressed Sensing for Image Reconstruction with Diffusion Probabilistic ModelsCode0
MetaEarth: A Generative Foundation Model for Global-Scale Remote Sensing Image Generation—0
FreeCustom: Tuning-Free Customized Image Generation for Multi-Concept CompositionCode2
Learning Latent Space Hierarchical EBM Diffusion Models—0
A Study of Posterior Stability for Time-Series Latent Diffusion—0
MotionCraft: Physics-based Zero-Shot Video GenerationCode1
Curriculum Direct Preference Optimization for Diffusion and Consistency ModelsCode0
I2I-Mamba: Multi-modal medical image synthesis via selective state space modelingCode2
Show:102550
← PrevPage 45 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