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 476500 of 6689 papers

TitleStatusHype
From Parts to Whole: A Unified Reference Framework for Controllable Human Image GenerationCode2
MultiBooth: Towards Generating All Your Concepts in an Image from TextCode2
Latent Guard: a Safety Framework for Text-to-image GenerationCode2
GeoSynth: Contextually-Aware High-Resolution Satellite Image SynthesisCode2
Diffusion-RWKV: Scaling RWKV-Like Architectures for Diffusion ModelsCode2
Dynamic Prompt Optimizing for Text-to-Image GenerationCode2
Score identity Distillation: Exponentially Fast Distillation of Pretrained Diffusion Models for One-Step GenerationCode2
CoMat: Aligning Text-to-Image Diffusion Model with Image-to-Text Concept MatchingCode2
No "Zero-Shot" Without Exponential Data: Pretraining Concept Frequency Determines Multimodal Model PerformanceCode2
Diffusion^2: Dynamic 3D Content Generation via Score Composition of Video and Multi-view Diffusion ModelsCode2
Texture-Preserving Diffusion Models for High-Fidelity Virtual Try-OnCode2
LAKE-RED: Camouflaged Images Generation by Latent Background Knowledge Retrieval-Augmented DiffusionCode2
Attention Calibration for Disentangled Text-to-Image PersonalizationCode2
LaRE^2: Latent Reconstruction Error Based Method for Diffusion-Generated Image DetectionCode2
Be Yourself: Bounded Attention for Multi-Subject Text-to-Image GenerationCode2
Open-Vocabulary Attention Maps with Token Optimization for Semantic Segmentation in Diffusion ModelsCode2
You Only Sample Once: Taming One-Step Text-to-Image Synthesis by Self-Cooperative Diffusion GANsCode2
Tuning-Free Image Customization with Image and Text GuidanceCode2
FouriScale: A Frequency Perspective on Training-Free High-Resolution Image SynthesisCode2
Generative Enhancement for 3D Medical ImagesCode2
CRS-Diff: Controllable Remote Sensing Image Generation with Diffusion ModelCode2
ThermoNeRF: Joint RGB and Thermal Novel View Synthesis for Building Facades using Multimodal Neural Radiance FieldsCode2
Boosting Flow-based Generative Super-Resolution Models via Learned PriorCode2
V_kD: Improving Knowledge Distillation using Orthogonal ProjectionsCode2
VidProM: A Million-scale Real Prompt-Gallery Dataset for Text-to-Video Diffusion ModelsCode2
Show:102550
← PrevPage 20 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