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 151–200 of 6689 papers

TitleStatusHype
Unleashing High-Quality Image Generation in Diffusion Sampling Using Second-Order Levenberg-Marquardt-LangevinCode1
Graph Flow Matching: Enhancing Image Generation with Neighbor-Aware Flow Fields—0
Category-aware EEG image generation based on wavelet transform and contrast semantic lossCode0
Multi-Group Proportional Representation for Text-to-Image Models—0
VisualSphinx: Large-Scale Synthetic Vision Logic Puzzles for RL—0
VITON-DRR: Details Retention Virtual Try-on via Non-rigid RegistrationCode0
Inference-time Scaling of Diffusion Models through Classical Search—0
Muddit: Liberating Generation Beyond Text-to-Image with a Unified Discrete Diffusion ModelCode2
R2I-Bench: Benchmarking Reasoning-Driven Text-to-Image Generation—0
LoRAShop: Training-Free Multi-Concept Image Generation and Editing with Rectified Flow Transformers—0
Diffusion Sampling Path Tells More: An Efficient Plug-and-Play Strategy for Sample FilteringCode0
RSFAKE-1M: A Large-Scale Dataset for Detecting Diffusion-Generated Remote Sensing Forgeries—0
Image Aesthetic Reasoning: A New Benchmark for Medical Image Screening with MLLMs—0
Implicit Inversion turns CLIP into a DecoderCode0
Dimension-Reduction Attack! Video Generative Models are Experts on Controllable Image Synthesis—0
How Animals Dance (When You're Not Looking)—0
Cross-modal RAG: Sub-dimensional Retrieval-Augmented Text-to-Image GenerationCode0
HiDream-I1: A High-Efficient Image Generative Foundation Model with Sparse Diffusion TransformerCode7
Principled Out-of-Distribution Generalization via Simplicity—0
Rhetorical Text-to-Image Generation via Two-layer Diffusion Policy Optimization—0
Uni-Instruct: One-step Diffusion Model through Unified Diffusion Divergence Instruction—0
DetailFlow: 1D Coarse-to-Fine Autoregressive Image Generation via Next-Detail PredictionCode2
Unveiling Impact of Frequency Components on Membership Inference Attacks for Diffusion Models—0
Creativity in LLM-based Multi-Agent Systems: A Survey—0
Applications and Effect Evaluation of Generative Adversarial Networks in Semi-Supervised Learning—0
FUDOKI: Discrete Flow-based Unified Understanding and Generation via Kinetic-Optimal Velocities—0
ImgEdit: A Unified Image Editing Dataset and BenchmarkCode4
Hierarchical Masked Autoregressive Models with Low-Resolution Token PivotsCode1
DiSA: Diffusion Step Annealing in Autoregressive Image GenerationCode2
MMIG-Bench: Towards Comprehensive and Explainable Evaluation of Multi-Modal Image Generation Models—0
StyleAR: Customizing Multimodal Autoregressive Model for Style-Aligned Text-to-Image Generation—0
Multimodal LLM-Guided Semantic Correction in Text-to-Image DiffusionCode1
Plug-and-Play Context Feature Reuse for Efficient Masked Generation—0
STRICT: Stress Test of Rendering Images Containing TextCode1
DriveX: Omni Scene Modeling for Learning Generalizable World Knowledge in Autonomous Driving—0
Towards Understanding the Mechanisms of Classifier-Free Guidance—0
MedITok: A Unified Tokenizer for Medical Image Synthesis and InterpretationCode1
TextDiffuser-RL: Efficient and Robust Text Layout Optimization for High-Fidelity Text-to-Image Synthesis—0
Training-free Stylized Text-to-Image Generation with Fast Inference—0
RAISE: Realness Assessment for Image Synthesis and EvaluationCode0
Test-Time Scaling of Diffusion Models via Noise Trajectory SearchCode0
Beyond Masked and Unmasked: Discrete Diffusion Models via Partial Masking—0
How to build a consistency model: Learning flow maps via self-distillation—0
TNG-CLIP:Training-Time Negation Data Generation for Negation Awareness of CLIP—0
OmniGenBench: A Benchmark for Omnipotent Multimodal Generation across 50+ TasksCode1
Mod-Adapter: Tuning-Free and Versatile Multi-concept Personalization via Modulation Adapter—0
Align Beyond Prompts: Evaluating World Knowledge Alignment in Text-to-Image GenerationCode0
MMMG: a Comprehensive and Reliable Evaluation Suite for Multitask Multimodal Generation—0
RePrompt: Reasoning-Augmented Reprompting for Text-to-Image Generation via Reinforcement LearningCode1
FutureSightDrive: Thinking Visually with Spatio-Temporal CoT for Autonomous Driving—0
Show:102550
← PrevPage 4 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