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 2401–2450 of 6689 papers

TitleStatusHype
Model-based Cleaning of the QUILT-1M Pathology Dataset for Text-Conditional Image SynthesisCode0
Generating Synthetic Satellite Imagery With Deep-Learning Text-to-Image Models -- Technical Challenges and Implications for Monitoring and Verification—0
Applying Guidance in a Limited Interval Improves Sample and Distribution Quality in Diffusion ModelsCode1
CAT: Contrastive Adapter Training for Personalized Image GenerationCode0
UDiFF: Generating Conditional Unsigned Distance Fields with Optimal Wavelet DiffusionCode1
Deep Generative Data Assimilation in Multimodal SettingCode1
A Gauss-Newton Approach for Min-Max Optimization in Generative Adversarial NetworksCode0
GeoSynth: Contextually-Aware High-Resolution Satellite Image SynthesisCode2
Hyperparameter-Free Medical Image Synthesis for Sharing Data and Improving Site-Specific SegmentationCode0
StoryImager: A Unified and Efficient Framework for Coherent Story Visualization and CompletionCode1
DiffHarmony: Latent Diffusion Model Meets Image HarmonizationCode1
High Noise Scheduling is a Must—0
Tackling Structural Hallucination in Image Translation with Local DiffusionCode1
Mask-ControlNet: Higher-Quality Image Generation with An Additional Mask Prompt—0
MoMA: Multimodal LLM Adapter for Fast Personalized Image GenerationCode3
UniFL: Improve Latent Diffusion Model via Unified Feedback Learning—0
Mind-to-Image: Projecting Visual Mental Imagination of the Brain from fMRI—0
Automatic Controllable Colorization via Imagination—0
SwapAnything: Enabling Arbitrary Object Swapping in Personalized Visual Editing—0
MC^2: Multi-concept Guidance for Customized Multi-concept GenerationCode1
StyleForge: Enhancing Text-to-Image Synthesis for Any Artistic Styles with Dual Binding—0
Strictly-ID-Preserved and Controllable Accessory Advertising Image Generation—0
ShoeModel: Learning to Wear on the User-specified Shoes via Diffusion Model—0
Contextual Chart Generation for Cyber Deception—0
Diffusion-RWKV: Scaling RWKV-Like Architectures for Diffusion ModelsCode2
Pixel-wise RL on Diffusion Models: Reinforcement Learning from Rich Feedback—0
Dynamic Prompt Optimizing for Text-to-Image GenerationCode2
PHISWID: Physics-Inspired Underwater Image Dataset Synthesized from RGB-D ImagesCode0
Score identity Distillation: Exponentially Fast Distillation of Pretrained Diffusion Models for One-Step GenerationCode2
Concept Weaver: Enabling Multi-Concept Fusion in Text-to-Image Models—0
No "Zero-Shot" Without Exponential Data: Pretraining Concept Frequency Determines Multimodal Model PerformanceCode2
Multi Positive Contrastive Learning with Pose-Consistent Generated Images—0
CoMat: Aligning Text-to-Image Diffusion Model with Image-to-Text Concept MatchingCode2
Diverse and Tailored Image Generation for Zero-shot Multi-label Classification—0
GaSpCT: Gaussian Splatting for Novel CT Projection View Synthesis—0
Would Deep Generative Models Amplify Bias in Future Models?—0
Reference-Based 3D-Aware Image Editing with Triplanes—0
InstantStyle: Free Lunch towards Style-Preserving in Text-to-Image GenerationCode7
Many-to-many Image Generation with Auto-regressive Diffusion Models—0
MatAtlas: Text-driven Consistent Geometry Texturing and Material Assignment—0
MULAN: A Multi Layer Annotated Dataset for Controllable Text-to-Image Generation—0
On the Scalability of Diffusion-based Text-to-Image Generation—0
Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale PredictionCode9
Heat Death of Generative Models in Closed-Loop Learning—0
Jailbreaking Prompt Attack: A Controllable Adversarial Attack against Diffusion Models—0
Diffusion^2: Dynamic 3D Content Generation via Score Composition of Video and Multi-view Diffusion ModelsCode2
Bi-LORA: A Vision-Language Approach for Synthetic Image DetectionCode1
Real, fake and synthetic faces - does the coin have three sides?—0
Model-Agnostic Human Preference Inversion in Diffusion Models—0
Towards Label-Efficient Human Matting: A Simple Baseline for Weakly Semi-Supervised Trimap-Free Human MattingCode0
Show:102550
← PrevPage 49 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