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 1301–1350 of 6689 papers

TitleStatusHype
HeadRouter: A Training-free Image Editing Framework for MM-DiTs by Adaptively Routing Attention Heads—0
Latent Schrodinger Bridge: Prompting Latent Diffusion for Fast Unpaired Image-to-Image Translation—0
Reconciling Semantic Controllability and Diversity for Remote Sensing Image Synthesis with Hybrid Semantic Embedding—0
High-Resolution Image Synthesis via Next-Token Prediction—0
Unsupervised Multi-view UAV Image Geo-localization via Iterative Rendering—0
Prioritize Denoising Steps on Diffusion Model Preference Alignment via Explicit Denoised Distribution Estimation—0
Learning Modality-Aware Representations: Adaptive Group-wise Interaction Network for Multimodal MRI SynthesisCode0
Exploiting Watermark-Based Defense Mechanisms in Text-to-Image Diffusion Models for Unauthorized Data Usage—0
Efficient Pruning of Text-to-Image Models: Insights from Pruning Stable Diffusion—0
Text Embedding is Not All You Need: Attention Control for Text-to-Image Semantic Alignment with Text Self-Attention Maps—0
ComfyGI: Automatic Improvement of Image Generation Workflows—0
Zero-Shot Low-Light Image Enhancement via Joint Frequency Domain Priors Guided DiffusionCode1
MMGenBench: Evaluating the Limits of LMMs from the Text-to-Image Generation PerspectiveCode2
Edge-Cloud Routing for Text-to-Image Model with Token-Level Multi-Metric Prediction—0
Safety Without Semantic Disruptions: Editing-free Safe Image Generation via Context-preserving Dual Latent Reconstruction—0
Detecting Human Artifacts from Text-to-Image ModelsCode1
Dealing with Synthetic Data Contamination in Online Continual LearningCode0
GalaxyEdit: Large-Scale Image Editing Dataset with Enhanced Diffusion Adapter—0
RAW-Diffusion: RGB-Guided Diffusion Models for High-Fidelity RAW Image GenerationCode2
CopyrightMeter: Revisiting Copyright Protection in Text-to-image Models—0
VBench++: Comprehensive and Versatile Benchmark Suite for Video Generative ModelsCode5
Adaptively Controllable Diffusion Model for Efficient Conditional Image Generation—0
HyperGAN-CLIP: A Unified Framework for Domain Adaptation, Image Synthesis and ManipulationCode2
Stylecodes: Encoding Stylistic Information For Image GenerationCode1
CCIS-Diff: A Generative Model with Stable Diffusion Prior for Controlled Colonoscopy Image Synthesis—0
Frequency-Aware Guidance for Blind Image Restoration via Diffusion Models—0
Enhancing Low Dose Computed Tomography Images Using Consistency Training Techniques—0
Constant Rate Schedule: Constant-Rate Distributional Change for Efficient Training and Sampling in Diffusion Models—0
From Text to Pose to Image: Improving Diffusion Model Control and QualityCode2
Decoupling Training-Free Guided Diffusion by ADMM—0
Zoomed In, Diffused Out: Towards Local Degradation-Aware Multi-Diffusion for Extreme Image Super-ResolutionCode0
Continuous Speculative Decoding for Autoregressive Image GenerationCode1
Cascaded Diffusion Models for 2D and 3D Microscopy Image Synthesis to Enhance Cell SegmentationCode0
BeautyBank: Encoding Facial Makeup in Latent Space—0
A Modular Open Source Framework for Genomic Variant Calling—0
Conceptwm: A Diffusion Model Watermark for Concept Protection—0
Enhanced Anime Image Generation Using USE-CMHSA-GAN—0
SageAttention2: Efficient Attention with Thorough Outlier Smoothing and Per-thread INT4 QuantizationCode7
Time Step Generating: A Universal Synthesized Deepfake Image DetectorCode0
Test-time Conditional Text-to-Image Synthesis Using Diffusion Models—0
Boundary Attention Constrained Zero-Shot Layout-To-Image Generation—0
SmoothCache: A Universal Inference Acceleration Technique for Diffusion TransformersCode1
CART: Compositional Auto-Regressive Transformer for Image Generation—0
Adaptive Non-Uniform Timestep Sampling for Diffusion Model Training—0
M-VAR: Decoupled Scale-wise Autoregressive Modeling for High-Quality Image GenerationCode2
Safe Text-to-Image Generation: Simply Sanitize the Prompt Embedding—0
Content-Aware Preserving Image Generation—0
Visual question answering based evaluation metrics for text-to-image generation—0
Advancing Diffusion Models: Alias-Free Resampling and Enhanced Rotational Equivariance—0
Image Regeneration: Evaluating Text-to-Image Model via Generating Identical Image with Multimodal Large Language Models—0
Show:102550
← PrevPage 27 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