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 31013125 of 6689 papers

TitleStatusHype
Images Speak Volumes: User-Centric Assessment of Image Generation for Accessible CommunicationCode0
Emerging Convolutions for Generative Normalizing FlowsCode0
Compensation Sampling for Improved Convergence in Diffusion ModelsCode0
Image Processing Using Multi-Code GAN PriorCode0
Image Style Transfer Using Convolutional Neural NetworksCode0
Image Translation for Medical Image Generation -- Ischemic Stroke LesionsCode0
Image Inpainting via Tractable Steering of Diffusion ModelsCode0
Image Generation Via Minimizing Fréchet Distance in Discriminator Feature SpaceCode0
Image Generation from Sketch Constraint Using Contextual GANCode0
Eliminating Contextual Prior Bias for Semantic Image Editing via Dual-Cycle DiffusionCode0
EliGen: Entity-Level Controlled Image Generation with Regional AttentionCode0
ASPIRE: Language-Guided Data Augmentation for Improving Robustness Against Spurious CorrelationsCode0
Image Difficulty Curriculum for Generative Adversarial Networks (CuGAN)Code0
Image Content Generation with Causal ReasoningCode0
Image Embedding for Denoising Generative ModelsCode0
Improving Explicit Spatial Relationships in Text-to-Image Generation through an Automatically Derived DatasetCode0
IntroVAE: Introspective Variational Autoencoders for Photographic Image SynthesisCode0
NiNformer: A Network in Network Transformer with Token Mixing Generated Gating FunctionCode0
Enhancing CT Image synthesis from multi-modal MRI data based on a multi-task neural network framework0
ComfyGPT: A Self-Optimizing Multi-Agent System for Comprehensive ComfyUI Workflow Generation0
Efficient-VQGAN: Towards High-Resolution Image Generation with Efficient Vision Transformers0
ComfyGI: Automatic Improvement of Image Generation Workflows0
Efficient Transfer Learning in Diffusion Models via Adversarial Noise0
ComfyGen: Prompt-Adaptive Workflows for Text-to-Image Generation0
Efficient Training with Denoised Neural Weights0
Show:102550
← PrevPage 125 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