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 176200 of 6689 papers

TitleStatusHype
FUDOKI: Discrete Flow-based Unified Understanding and Generation via Kinetic-Optimal Velocities0
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 Models0
StyleAR: Customizing Multimodal Autoregressive Model for Style-Aligned Text-to-Image Generation0
Multimodal LLM-Guided Semantic Correction in Text-to-Image DiffusionCode1
Plug-and-Play Context Feature Reuse for Efficient Masked Generation0
STRICT: Stress Test of Rendering Images Containing TextCode1
DriveX: Omni Scene Modeling for Learning Generalizable World Knowledge in Autonomous Driving0
Towards Understanding the Mechanisms of Classifier-Free Guidance0
MedITok: A Unified Tokenizer for Medical Image Synthesis and InterpretationCode1
TextDiffuser-RL: Efficient and Robust Text Layout Optimization for High-Fidelity Text-to-Image Synthesis0
Training-free Stylized Text-to-Image Generation with Fast Inference0
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 Masking0
How to build a consistency model: Learning flow maps via self-distillation0
TNG-CLIP:Training-Time Negation Data Generation for Negation Awareness of CLIP0
OmniGenBench: A Benchmark for Omnipotent Multimodal Generation across 50+ TasksCode1
Mod-Adapter: Tuning-Free and Versatile Multi-concept Personalization via Modulation Adapter0
Align Beyond Prompts: Evaluating World Knowledge Alignment in Text-to-Image GenerationCode0
MMMG: a Comprehensive and Reliable Evaluation Suite for Multitask Multimodal Generation0
RePrompt: Reasoning-Augmented Reprompting for Text-to-Image Generation via Reinforcement LearningCode1
FutureSightDrive: Thinking Visually with Spatio-Temporal CoT for Autonomous Driving0
Show:102550
← PrevPage 8 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