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 3701–3750 of 6689 papers

TitleStatusHype
Energy-Efficient Downlink Semantic Generative Communication with Text-to-Image Generators—0
SyncDiffusion: Coherent Montage via Synchronized Joint Diffusions—0
Grounded Text-to-Image Synthesis with Attention Refocusing—0
Rewarded soups: towards Pareto-optimal alignment by interpolating weights fine-tuned on diverse rewardsCode1
Exposing flaws of generative model evaluation metrics and their unfair treatment of diffusion modelsCode2
Designing a Better Asymmetric VQGAN for StableDiffusionCode3
GeoDiffusion: Text-Prompted Geometric Control for Object Detection Data Generation—0
DreamSparse: Escaping from Plato's Cave with 2D Frozen Diffusion Model Given Sparse Views—0
Conditional Diffusion Models for Weakly Supervised Medical Image SegmentationCode1
On the Difference of BERT-style and CLIP-style Text EncodersCode1
Semantically-Prompted Language Models Improve Visual Descriptions—0
Discovering Novel Biological Traits From Images Using Phylogeny-Guided Neural NetworksCode0
Composition and Deformance: Measuring Imageability with a Text-to-Image ModelCode0
Cheap-fake Detection with LLM using Prompt Engineering—0
A Vessel-Segmentation-Based CycleGAN for Unpaired Multi-modal Retinal Image Synthesis—0
Brain Diffusion for Visual Exploration: Cortical Discovery using Large Scale Generative Models—0
Microscopy image reconstruction with physics-informed denoising diffusion probabilistic modelCode1
Detector Guidance for Multi-Object Text-to-Image GenerationCode1
VideoComposer: Compositional Video Synthesis with Motion ControllabilityCode2
Table and Image Generation for Investigating Knowledge of Entities in Pre-trained Vision and Language ModelsCode0
Unlearnable Examples for Diffusion Models: Protect Data from Unauthorized Exploitation—0
The Surprising Effectiveness of Diffusion Models for Optical Flow and Monocular Depth Estimation—0
Conditional Generation from Unconditional Diffusion Models using Denoiser RepresentationsCode0
The Information Pathways Hypothesis: Transformers are Dynamic Self-EnsemblesCode1
An Attentive-based Generative Model for Medical Image SynthesisCode1
Diffusion Self-Guidance for Controllable Image GenerationCode1
Evaluating the Capabilities of Multi-modal Reasoning Models with Synthetic Task Data—0
Extracting Reward Functions from Diffusion ModelsCode1
ReFACT: Updating Text-to-Image Models by Editing the Text EncoderCode1
Interactive Character Control with Auto-Regressive Motion Diffusion ModelsCode1
Make-Your-Video: Customized Video Generation Using Textual and Structural Guidance—0
Discovering Failure Modes of Text-guided Diffusion Models via Adversarial Search—0
STEVE-1: A Generative Model for Text-to-Behavior in MinecraftCode2
Intelligent Grimm -- Open-ended Visual Storytelling via Latent Diffusion ModelsCode2
UniDiff: Advancing Vision-Language Models with Generative and Discriminative Learning—0
T2IAT: Measuring Valence and Stereotypical Biases in Text-to-Image Generation—0
Image generation with shortest path diffusionCode1
Wuerstchen: An Efficient Architecture for Large-Scale Text-to-Image Diffusion ModelsCode2
Differential Diffusion: Giving Each Pixel Its StrengthCode2
ViCo: Plug-and-play Visual Condition for Personalized Text-to-image GenerationCode2
StyleDrop: Text-to-Image Generation in Any StyleCode2
Cocktail: Mixing Multi-Modality Controls for Text-Conditional Image Generation—0
Learning Disentangled Prompts for Compositional Image SynthesisCode1
DiffInDScene: Diffusion-based High-Quality 3D Indoor Scene GenerationCode1
AI Imagery and the Overton Window—0
Manifold Constraint Regularization for Remote Sensing Image Generation—0
Tree-Ring Watermarks: Fingerprints for Diffusion Images that are Invisible and RobustCode2
Inferring and Leveraging Parts from Object Shape for Improving Semantic Image SynthesisCode1
A Unified Conditional Framework for Diffusion-based Image Restoration—0
Real-World Image Variation by Aligning Diffusion Inversion ChainCode1
Show:102550
← PrevPage 75 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