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 501–550 of 6689 papers

TitleStatusHype
3DGen-Bench: Comprehensive Benchmark Suite for 3D Generative Models—0
UGen: Unified Autoregressive Multimodal Model with Progressive Vocabulary Learning—0
Model as a Game: On Numerical and Spatial Consistency for Generative Games—0
CTRL-O: Language-Controllable Object-Centric Visual Representation Learning—0
Unified Multimodal Discrete DiffusionCode2
High Quality Diffusion Distillation on a Single GPU with Relative and Absolute Position Matching—0
BizGen: Advancing Article-level Visual Text Rendering for Infographics Generation—0
MMGen: Unified Multi-modal Image Generation and Understanding in One Go—0
RecTable: Fast Modeling Tabular Data with Rectified FlowCode0
Beyond Words: Advancing Long-Text Image Generation via Multimodal Autoregressive Models—0
Dissecting and Mitigating Diffusion Bias via Mechanistic InterpretabilityCode1
Learning Hazing to Dehazing: Towards Realistic Haze Generation for Real-World Image DehazingCode2
Exploring Disentangled and Controllable Human Image Synthesis: From End-to-End to Stage-by-Stage—0
LayerCraft: Enhancing Text-to-Image Generation with CoT Reasoning and Layered Object IntegrationCode0
VectorFit : Adaptive Singular & Bias Vector Fine-Tuning of Pre-trained Foundation Models—0
SITA: Structurally Imperceptible and Transferable Adversarial Attacks for Stylized Image GenerationCode0
Scaling Down Text Encoders of Text-to-Image Diffusion ModelsCode2
PCM : Picard Consistency Model for Fast Parallel Sampling of Diffusion Models—0
Reverse Prompt: Cracking the Recipe Inside Text-to-Image Generation—0
U-REPA: Aligning Diffusion U-Nets to ViTsCode1
PALATE: Peculiar Application of the Law of Total Expectation to Enhance the Evaluation of Deep Generative ModelsCode0
Diffusion-4K: Ultra-High-Resolution Image Synthesis with Latent Diffusion ModelsCode3
Training-free Diffusion Acceleration with Bottleneck Sampling—0
Latent Space Super-Resolution for Higher-Resolution Image Generation with Diffusion ModelsCode1
Plug-and-Play Interpretable Responsible Text-to-Image Generation via Dual-Space Multi-facet Concept Control—0
Boosting Resolution Generalization of Diffusion Transformers with Randomized Positional Encodings—0
Equivariant Image ModelingCode1
An Image-like Diffusion Method for Human-Object Interaction Detection—0
DeLoRA: Decoupling Angles and Strength in Low-rank AdaptationCode1
TransAnimate: Taming Layer Diffusion to Generate RGBA Video—0
Unseen from Seen: Rewriting Observation-Instruction Using Foundation Models for Augmenting Vision-Language NavigationCode1
Adoption of Watermarking Measures for AI-Generated Content and Implications under the EU AI Act—0
TCFG: Tangential Damping Classifier-free Guidance—0
Efficient Diffusion Training through Parallelization with Truncated Karhunen-Loève Expansion—0
DynASyn: Multi-Subject Personalization Enabling Dynamic Action Synthesis—0
TDRI: Two-Phase Dialogue Refinement and Co-Adaptation for Interactive Image Generation—0
OMR-Diffusion:Optimizing Multi-Round Enhanced Training in Diffusion Models for Improved Intent Understanding—0
FundusGAN: A Hierarchical Feature-Aware Generative Framework for High-Fidelity Fundus Image Generation—0
ComfyGPT: A Self-Optimizing Multi-Agent System for Comprehensive ComfyUI Workflow Generation—0
End-to-end Sketch-Guided Path Planning through Imitation Learning for Autonomous Mobile RobotsCode0
Halton Scheduler For Masked Generative Image TransformerCode3
D2C: Unlocking the Potential of Continuous Autoregressive Image Generation with Discrete Tokens—0
Bayesian generative models can flag performance loss, bias, and out-of-distribution image content—0
Zero-Shot Styled Text Image Generation, but Make It Autoregressive—0
Leveraging Text-to-Image Generation for Handling Spurious Correlation—0
EDiT: Efficient Diffusion Transformers with Linear Compressed Attention—0
World Knowledge from AI Image Generation for Robot Control—0
InfiniteYou: Flexible Photo Recrafting While Preserving Your IdentityCode7
Tokenize Image as a SetCode2
RL4Med-DDPO: Reinforcement Learning for Controlled Guidance Towards Diverse Medical Image Generation using Vision-Language Foundation Models—0
Show:102550
← PrevPage 11 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