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 1201–1250 of 6689 papers

TitleStatusHype
Partially Conditioned Patch Parallelism for Accelerated Diffusion Model Inference—0
DynamicControl: Adaptive Condition Selection for Improved Text-to-Image Generation—0
Multi-view Image Diffusion via Coordinate Noise and Fourier Attention—0
Flow Matching with General Discrete Paths: A Kinetic-Optimal Perspective—0
ShapeWords: Guiding Text-to-Image Synthesis with 3D Shape-Aware Prompts—0
SNOOPI: Supercharged One-step Diffusion Distillation with Proper Guidance—0
GIST: Towards Photorealistic Style Transfer via Multiscale Geometric Representations—0
Generative Photography: Scene-Consistent Camera Control for Realistic Text-to-Image SynthesisCode2
3D representation in 512-Byte:Variational tokenizer is the key for autoregressive 3D generation—0
FoundHand: Large-Scale Domain-Specific Learning for Controllable Hand Image Generation—0
WEM-GAN: Wavelet transform based facial expression manipulation—0
AccDiffusion v2: Towards More Accurate Higher-Resolution Diffusion ExtrapolationCode1
ScImage: How Good Are Multimodal Large Language Models at Scientific Text-to-Image Generation?Code0
Taming Scalable Visual Tokenizer for Autoregressive Image GenerationCode4
Cross-Attention Head Position Patterns Can Align with Human Visual Concepts in Text-to-Image Generative ModelsCode1
Hierarchical VAE with a Diffusion-based VampPriorCode0
Fréchet Radiomic Distance (FRD): A Versatile Metric for Comparing Medical Imaging DatasetsCode1
MFTF: Mask-free Training-free Object Level Layout Control Diffusion ModelCode0
LoyalDiffusion: A Diffusion Model Guarding Against Data Replication—0
OmniFlow: Any-to-Any Generation with Multi-Modal Rectified FlowsCode2
SerialGen: Personalized Image Generation by First Standardization Then Personalization—0
TinyFusion: Diffusion Transformers Learned ShallowCode2
MuLan: Adapting Multilingual Diffusion Models for Hundreds of Languages with Negligible CostCode3
Switti: Designing Scale-Wise Transformers for Text-to-Image Synthesis—0
World-consistent Video Diffusion with Explicit 3D Modeling—0
Schedule On the Fly: Diffusion Time Prediction for Faster and Better Image Generation—0
CopyrightShield: Spatial Similarity Guided Backdoor Defense against Copyright Infringement in Diffusion Models—0
IQA-Adapter: Exploring Knowledge Transfer from Image Quality Assessment to Diffusion-based Generative ModelsCode1
Concept Replacer: Replacing Sensitive Concepts in Diffusion Models via Precision LocalizationCode0
X-Prompt: Towards Universal In-Context Image Generation in Auto-Regressive Vision Language Foundation ModelsCode2
TextSSR: Diffusion-based Data Synthesis for Scene Text RecognitionCode2
Memories of Forgotten Concepts—0
Playable Game GenerationCode2
CtrlNeRF: The Generative Neural Radiation Fields for the Controllable Synthesis of High-fidelity 3D-Aware Images—0
Learning on Less: Constraining Pre-trained Model Learning for Generalizable Diffusion-Generated Image Detection—0
AniMer: Animal Pose and Shape Estimation Using Family Aware Transformer—0
Energy-Based Prior Latent Space Diffusion model for Reconstruction of Lumbar Vertebrae from Thick Slice MRICode0
QUOTA: Quantifying Objects with Text-to-Image Models for Any Domain—0
Opt-In Art: Learning Art Styles Only from Few Examples—0
Retrieval-guided Cross-view Image Synthesis—0
TexGaussian: Generating High-quality PBR Material via Octree-based 3D Gaussian SplattingCode2
JetFormer: An Autoregressive Generative Model of Raw Images and Text—0
Uniform Attention Maps: Boosting Image Fidelity in Reconstruction and EditingCode1
3D-WAG: Hierarchical Wavelet-Guided Autoregressive Generation for High-Fidelity 3D Shapes—0
Improving Multi-Subject Consistency in Open-Domain Image Generation with Isolation and Reposition Attention—0
Self-Cross Diffusion Guidance for Text-to-Image Synthesis of Similar Subjects—0
DreamBlend: Advancing Personalized Fine-tuning of Text-to-Image Diffusion Models—0
Locally-Focused Face Representation for Sketch-to-Image Generation Using Noise-Induced Refinement—0
SOWing Information: Cultivating Contextual Coherence with MLLMs in Image Generation—0
AMO Sampler: Enhancing Text Rendering with OvershootingCode1
Show:102550
← PrevPage 25 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