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 3351–3400 of 6689 papers

TitleStatusHype
Towards Few-Call Model Stealing via Active Self-Paced Knowledge Distillation and Diffusion-Based Image Generation—0
Text-image Alignment for Diffusion-based PerceptionCode1
Consistency Models as a Rich and Efficient Policy Class for Reinforcement LearningCode1
Denoising Diffusion Bridge ModelsCode2
CCEdit: Creative and Controllable Video Editing via Diffusion ModelsCode1
Exposing Image Splicing Traces in Scientific Publications via Uncertainty-guided RefinementCode0
Emu: Enhancing Image Generation Models Using Photogenic Needles in a Haystack—0
Finite Scalar Quantization: VQ-VAE Made SimpleCode1
Factorized Diffusion Architectures for Unsupervised Image Generation and Segmentation—0
Position and Orientation-Aware One-Shot Learning for Medical Action Recognition from Signal Data—0
DreamCom: Finetuning Text-guided Inpainting Model for Image Composition—0
Jointly Training Large Autoregressive Multimodal Models—0
Guided Frequency Loss for Image Restoration—0
Teaching Text-to-Image Models to Communicate in Dialog—0
Text-to-Image Generation for Abstract Concepts—0
VideoDirectorGPT: Consistent Multi-scene Video Generation via LLM-Guided Planning—0
In-Domain GAN Inversion for Faithful Reconstruction and Editability—0
Soft Mixture Denoising: Beyond the Expressive Bottleneck of Diffusion Models—0
Diverse Semantic Image Editing with Style CodesCode0
Chop & Learn: Recognizing and Generating Object-State Compositions—0
Randomize to Generalize: Domain Randomization for Runway FOD Detection—0
MISFIT-V: Misaligned Image Synthesis and Fusion using Information from Thermal and VisualCode0
TextCLIP: Text-Guided Face Image Generation And Manipulation Without Adversarial Training—0
Understanding Pose and Appearance Disentanglement in 3D Human Pose Estimation—0
Distilling Adversarial Prompts from Safety Benchmarks: Report for the Adversarial Nibbler Challenge—0
Latent Diffusion Models for Structural Component Design—0
Language-Oriented Communication with Semantic Coding and Knowledge Distillation for Text-to-Image Generation—0
AutoDiffusion: Training-Free Optimization of Time Steps and Architectures for Automated Diffusion Model AccelerationCode1
SideGAN: 3D-Aware Generative Model for Improved Side-View Image Synthesis—0
Diffusion Models for Accurate Channel Distribution Generation—0
Language Guided Adversarial PurificationCode0
Assessing the capacity of a denoising diffusion probabilistic model to reproduce spatial context—0
Multimodal Foundation Models: From Specialists to General-Purpose AssistantsCode3
Progressive Text-to-Image Diffusion with Soft Latent DirectionCode1
Gradpaint: Gradient-Guided Inpainting with Diffusion Models—0
Causal-Story: Local Causal Attention Utilizing Parameter-Efficient Tuning For Visual Story Synthesis—0
Cartoondiff: Training-free Cartoon Image Generation with Diffusion Transformer Models—0
MetaF2N: Blind Image Super-Resolution by Learning Efficient Model Adaptation from FacesCode1
Increasing diversity of omni-directional images generated from single image using cGAN based on MLPMixerCode0
M3Dsynth: A dataset of medical 3D images with AI-generated local manipulationsCode0
Viewpoint Textual Inversion: Discovering Scene Representations and 3D View Control in 2D Diffusion ModelsCode0
Limitations of Face Image GenerationCode0
MagiCapture: High-Resolution Multi-Concept Portrait Customization—0
DreamStyler: Paint by Style Inversion with Text-to-Image Diffusion Models—0
Deep Nonparametric Convexified Filtering for Computational Photography, Image Synthesis and Adversarial Defense—0
Beyond Generation: Harnessing Text to Image Models for Object Detection and SegmentationCode1
InstaFlow: One Step is Enough for High-Quality Diffusion-Based Text-to-Image GenerationCode3
Language Models as Black-Box Optimizers for Vision-Language ModelsCode1
Elucidating the solution space of extended reverse-time SDE for diffusion modelsCode1
PhotoVerse: Tuning-Free Image Customization with Text-to-Image Diffusion ModelsCode1
Show:102550
← PrevPage 68 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