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 1651–1700 of 6689 papers

TitleStatusHype
Adaptive Feature Interpolation for Low-Shot Image GenerationCode1
Diffusion-based Blind Text Image Super-ResolutionCode1
Enhancing Semantic Fidelity in Text-to-Image Synthesis: Attention Regulation in Diffusion ModelsCode1
Cached Multi-Lora Composition for Multi-Concept Image GenerationCode1
Elucidating the solution space of extended reverse-time SDE for diffusion modelsCode1
Diffusion-based Image Generation for In-distribution Data Augmentation in Surface Defect DetectionCode1
Continuous Speculative Decoding for Autoregressive Image GenerationCode1
Diffusion-Based Scene Graph to Image Generation with Masked Contrastive Pre-TrainingCode1
Embedding an Ethical Mind: Aligning Text-to-Image Synthesis via Lightweight Value OptimizationCode1
Continuous Language Generative FlowCode1
Improved Contrastive Divergence Training of Energy Based ModelsCode1
DiffusionCLIP: Text-Guided Diffusion Models for Robust Image ManipulationCode1
3D-Aware Semantic-Guided Generative Model for Human SynthesisCode1
Elucidating the Exposure Bias in Diffusion ModelsCode1
Maximum Likelihood Training of Implicit Nonlinear Diffusion ModelsCode1
Diffusion Curriculum: Synthetic-to-Real Generative Curriculum Learning via Image-Guided DiffusionCode1
Diffusion Deformable Model for 4D Temporal Medical Image GenerationCode1
Improved Techniques for Training Single-Image GANsCode1
Improved Training of Wasserstein GANsCode1
Membership Inference on Text-to-Image Diffusion Models via Conditional Likelihood DiscrepancyCode1
MM2Latent: Text-to-facial image generation and editing in GANs with multimodal assistanceCode1
MUSES: 3D-Controllable Image Generation via Multi-Modal Agent CollaborationCode1
DiffusionFace: Towards a Comprehensive Dataset for Diffusion-Based Face Forgery AnalysisCode1
Continual Learning of Diffusion Models with Generative DistillationCode1
ConTEXTual Net: A Multimodal Vision-Language Model for Segmentation of PneumothoraxCode1
Attribute-guided image generation from layoutCode1
Contextual Convolutional Neural NetworksCode1
Inversion Circle Interpolation: Diffusion-based Image Augmentation for Data-scarce ClassificationCode1
Attribute Group Editing for Reliable Few-shot Image GenerationCode1
Masked Diffusion Models Are Fast Distribution LearnersCode1
EHRDiff: Exploring Realistic EHR Synthesis with Diffusion ModelsCode1
Improving GAN Training with Probability Ratio Clipping and Sample ReweightingCode1
Improving Relational Regularized Autoencoders with Spherical Sliced Fused Gromov WassersteinCode1
Context-Aware Layout to Image Generation with Enhanced Object AppearanceCode1
EigenGAN: Layer-Wise Eigen-Learning for GANsCode1
EGC: Image Generation and Classification via a Diffusion Energy-Based ModelCode1
AITTI: Learning Adaptive Inclusive Token for Text-to-Image GenerationCode1
ElasticDiffusion: Training-free Arbitrary Size Image Generation through Global-Local Content SeparationCode1
Adversarial Audio SynthesisCode1
Diffusion Models Beat GANs on Image ClassificationCode1
Efficient Scale-Invariant Generator with Column-Row Entangled Pixel SynthesisCode1
Mask-conditioned latent diffusion for generating gastrointestinal polyp imagesCode1
Efficient Neural Architecture for Text-to-Image SynthesisCode1
Can MLLMs Perform Text-to-Image In-Context Learning?Code1
AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial NetworksCode1
Memory-Efficient 3D Denoising Diffusion Models for Medical Image ProcessingCode1
Efficient Personalization of Quantized Diffusion Model without BackpropagationCode1
Masked and Adaptive Transformer for Exemplar Based Image TranslationCode1
Content-Aware GAN CompressionCode1
3D-aware Image Synthesis via Learning Structural and Textural RepresentationsCode1
Show:102550
← PrevPage 34 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