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 2651–2700 of 6689 papers

TitleStatusHype
Optimal Stochastic Trace Estimation in Generative Modeling—0
AI-Instruments: Embodying Prompts as Instruments to Abstract & Reflect Graphical Interface Commands as General-Purpose Tools—0
Bayesian Optimization for Controlled Image Editing via LLMs—0
Robust Polyp Detection and Diagnosis through Compositional Prompt-Guided Diffusion Models—0
FoREST: Frame of Reference Evaluation in Spatial Reasoning TasksCode0
ASurvey: Spatiotemporal Consistency in Video Generation—0
LDGen: Enhancing Text-to-Image Synthesis via Large Language Model-Driven Language Representation—0
Distributional Vision-Language Alignment by Cauchy-Schwarz Divergence—0
A Pragmatic Note on Evaluating Generative Models with Fréchet Inception Distance for Retinal Image Synthesis—0
SynthRAD2025 Grand Challenge dataset: generating synthetic CTs for radiotherapy—0
Culture-TRIP: Culturally-Aware Text-to-Image Generation with Iterative Prompt Refinement—0
Autoregressive Image Generation Guided by Chains of Thought—0
RELICT: A Replica Detection Framework for Medical Image GenerationCode0
High-resolution Rainy Image Synthesis: Learning from RenderingCode0
Unified Prompt Attack Against Text-to-Image Generation Models—0
Iterative Flow Matching -- Path Correction and Gradual Refinement for Enhanced Generative Modeling—0
DualNeRF: Text-Driven 3D Scene Editing via Dual-Field Representation—0
One-step Diffusion Models with f-Divergence Distribution Matching—0
Multi-Agent Multimodal Models for Multicultural Text to Image GenerationCode0
FlipConcept: Tuning-Free Multi-Concept Personalization for Text-to-Image Generation—0
Improving the Diffusability of Autoencoders—0
Generative Modeling of Individual Behavior at Scale—0
DC-ControlNet: Decoupling Inter- and Intra-Element Conditions in Image Generation with Diffusion Models—0
MagicGeo: Training-Free Text-Guided Geometric Diagram Generation—0
Flow-based generative models as iterative algorithms in probability space—0
FlexTok: Resampling Images into 1D Token Sequences of Flexible Length—0
IP-Composer: Semantic Composition of Visual Concepts—0
Flow-of-Options: Diversified and Improved LLM Reasoning by Thinking Through OptionsCode0
Spherical Dense Text-to-Image Synthesis—0
GRAPHGPT-O: Synergistic Multimodal Comprehension and Generation on Graphs—0
A Survey on Bridging EEG Signals and Generative AI: From Image and Text to Beyond—0
Multi-Faceted Multimodal Monosemanticity—0
ManiTrend: Bridging Future Generation and Action Prediction with 3D Flow for Robotic Manipulation—0
SWA-LDM: Toward Stealthy Watermarks for Latent Diffusion ModelsCode0
Redistribute Ensemble Training for Mitigating Memorization in Diffusion ModelsCode0
Detecting Malicious Concepts Without Image Generation in AIGC—0
Designing a Conditional Prior Distribution for Flow-Based Generative Models—0
ImageRAG: Dynamic Image Retrieval for Reference-Guided Image Generation—0
When the LM misunderstood the human chuckled: Analyzing garden path effects in humans and language models—0
EQ-VAE: Equivariance Regularized Latent Space for Improved Generative Image Modeling—0
PoGDiff: Product-of-Gaussians Diffusion Models for Imbalanced Text-to-Image Generation—0
Ultrasound Image Generation using Latent Diffusion Models—0
ID-Cloak: Crafting Identity-Specific Cloaks Against Personalized Text-to-Image Generation—0
Skrr: Skip and Re-use Text Encoder Layers for Memory Efficient Text-to-Image Generation—0
BCDDM: Branch-Corrected Denoising Diffusion Model for Black Hole Image Generation—0
A Survey on Pre-Trained Diffusion Model Distillations—0
Enhancing Diffusion Models Efficiency by Disentangling Total-Variance and Signal-to-Noise RatioCode0
Articulate That Object Part (ATOP): 3D Part Articulation from Text and Motion Personalization—0
Classifier-Free Guidance: From High-Dimensional Analysis to Generalized Guidance Forms—0
CausalGeD: Blending Causality and Diffusion for Spatial Gene Expression Generation—0
Show:102550
← PrevPage 54 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