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 776800 of 6689 papers

TitleStatusHype
Aligning Generative Denoising with Discriminative Objectives Unleashes Diffusion for Visual PerceptionCode1
Anchor Token Matching: Implicit Structure Locking for Training-free AR Image EditingCode1
GeoUni: A Unified Model for Generating Geometry Diagrams, Problems and Problem SolutionsCode1
Omni-Dish: Photorealistic and Faithful Image Generation and Editing for Arbitrary Chinese DishesCode1
LMM4LMM: Benchmarking and Evaluating Large-multimodal Image Generation with LMMsCode1
Latent Diffusion Autoencoders: Toward Efficient and Meaningful Unsupervised Representation Learning in Medical ImagingCode1
ID-Booth: Identity-consistent Face Generation with Diffusion ModelsCode1
A Unified Agentic Framework for Evaluating Conditional Image GenerationCode1
DyDiT++: Dynamic Diffusion Transformers for Efficient Visual GenerationCode1
An Empirical Study of GPT-4o Image Generation CapabilitiesCode1
Mind the Trojan Horse: Image Prompt Adapter Enabling Scalable and Deceptive JailbreakingCode1
MergeVQ: A Unified Framework for Visual Generation and Representation with Disentangled Token Merging and QuantizationCode1
Dissecting and Mitigating Diffusion Bias via Mechanistic InterpretabilityCode1
Equivariant Image ModelingCode1
U-REPA: Aligning Diffusion U-Nets to ViTsCode1
Latent Space Super-Resolution for Higher-Resolution Image Generation with Diffusion ModelsCode1
DeLoRA: Decoupling Angles and Strength in Low-rank AdaptationCode1
Unseen from Seen: Rewriting Observation-Instruction Using Foundation Models for Augmenting Vision-Language NavigationCode1
Multi-focal Conditioned Latent Diffusion for Person Image SynthesisCode1
Efficient Personalization of Quantized Diffusion Model without BackpropagationCode1
SimWorld: A Unified Benchmark for Simulator-Conditioned Scene Generation via World ModelCode1
DPImageBench: A Unified Benchmark for Differentially Private Image SynthesisCode1
Localized Concept Erasure for Text-to-Image Diffusion Models Using Training-Free Gated Low-Rank AdaptationCode1
Harnessing Frequency Spectrum Insights for Image Copyright Protection Against Diffusion ModelsCode1
AdvPaint: Protecting Images from Inpainting Manipulation via Adversarial Attention DisruptionCode1
Show:102550
← PrevPage 32 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