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 26–50 of 6689 papers

TitleStatusHype
DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World KnowledgeCode3
A Training-Free Style-Personalization via Scale-wise Autoregressive Model—0
Flow-Anchored Consistency ModelsCode2
Hita: Holistic Tokenizer for Autoregressive Image GenerationCode0
UniMC: Taming Diffusion Transformer for Unified Keypoint-Guided Multi-Class Image Generation—0
Rethinking Discrete Tokens: Treating Them as Conditions for Continuous Autoregressive Image Synthesis—0
Locality-aware Parallel Decoding for Efficient Autoregressive Image Generation—0
Process-aware and high-fidelity microstructure generation using stable diffusion—0
UniGlyph: Unified Segmentation-Conditioned Diffusion for Precise Visual Text Synthesis—0
CycleVAR: Repurposing Autoregressive Model for Unsupervised One-Step Image TranslationCode1
Ovis-U1 Technical ReportCode3
Prompt Mechanisms in Medical Imaging: A Comprehensive Survey—0
ODE_t (ODE_l ): Shortcutting the Time and Length in Diffusion and Flow Models for Faster SamplingCode0
Instella-T2I: Pushing the Limits of 1D Discrete Latent Space Image Generation—0
GenFlow: Interactive Modular System for Image Generation—0
Rethink Sparse Signals for Pose-guided Text-to-image GenerationCode0
XVerse: Consistent Multi-Subject Control of Identity and Semantic Attributes via DiT ModulationCode4
BitMark for Infinity: Watermarking Bitwise Autoregressive Image Generative Models—0
Improving Diffusion-Based Image Editing Faithfulness via Guidance and Scheduling—0
HybridQ: Hybrid Classical-Quantum Generative Adversarial Network for Skin Disease Image Generation—0
Diffusion Tree Sampling: Scalable inference-time alignment of diffusion models—0
MultiHuman-Testbench: Benchmarking Image Generation for Multiple Humans—0
3DGH: 3D Head Generation with Composable Hair and Face—0
HiWave: Training-Free High-Resolution Image Generation via Wavelet-Based Diffusion Sampling—0
Med-Art: Diffusion Transformer for 2D Medical Text-to-Image Generation—0
Show:102550
← PrevPage 2 of 268Next →
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