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 2501–2550 of 6689 papers

TitleStatusHype
Grimm in Wonderland: Prompt Engineering with Midjourney to Illustrate Fairytales—0
Dimba: Transformer-Mamba Diffusion Models—0
Applications and Effect Evaluation of Generative Adversarial Networks in Semi-Supervised Learning—0
Di[M]O: Distilling Masked Diffusion Models into One-step Generator—0
Application of Unsupervised Domain Adaptation for Structural MRI Analysis—0
DilateQuant: Accurate and Efficient Diffusion Quantization via Weight Dilation—0
Dilated POCS: Minimax Convex Optimization—0
CASIA-Face-Africa: A Large-scale African Face Image Database—0
Digital Gene: Learning about the Physical World through Analytic Concepts—0
Cascading Modular Network (CAM-Net) for Multimodal Image Synthesis—0
DRAGON: A Large-Scale Dataset of Realistic Images Generated by Diffusion Models—0
DiFiC: Your Diffusion Model Holds the Secret to Fine-Grained Clustering—0
Cascaded Diffusion Models for High Fidelity Image Generation—0
DiffVSR: Enhancing Real-World Video Super-Resolution with Diffusion Models for Advanced Visual Quality and Temporal Consistency—0
Appearance Matching Adapter for Exemplar-based Semantic Image Synthesis—0
DiffuVST: Narrating Fictional Scenes with Global-History-Guided Denoising Models—0
Diffutoon: High-Resolution Editable Toon Shading via Diffusion Models—0
Make VLM Recognize Visual Hallucination on Cartoon Character Image with Pose Information—0
DiffusionTrend: A Minimalist Approach to Virtual Fashion Try-On—0
Diffusion Tree Sampling: Scalable inference-time alignment of diffusion models—0
Cartoondiff: Training-free Cartoon Image Generation with Diffusion Transformer Models—0
Appearance Harmonization for Single Image Shadow Removal—0
GRIN: Zero-Shot Metric Depth with Pixel-Level Diffusion—0
Guardians of Generation: Dynamic Inference-Time Copyright Shielding with Adaptive Guidance for AI Image Generation—0
Diffusion-Stego: Training-free Diffusion Generative Steganography via Message Projection—0
Diffusion Soup: Model Merging for Text-to-Image Diffusion Models—0
Adversarial Domain Prompt Tuning and Generation for Single Domain Generalization—0
Diffusion Self-Distillation for Zero-Shot Customized Image Generation—0
CART: Compositional Auto-Regressive Transformer for Image Generation—0
Investigating Object Compositionality in Generative Adversarial Networks—0
Diffusion-SDF: Conditional Generative Modeling of Signed Distance Functions—0
Diffusion Schrödinger Bridge Models for High-Quality MR-to-CT Synthesis for Head and Neck Proton Treatment Planning—0
Cardiac ultrasound simulation for autonomous ultrasound navigation—0
Graph Flow Matching: Enhancing Image Generation with Neighbor-Aware Flow Fields—0
GRAPHGPT-O: Synergistic Multimodal Comprehension and Generation on Graphs—0
A Pipeline for Vision-Based On-Orbit Proximity Operations Using Deep Learning and Synthetic Imagery—0
GRAM-HD: 3D-Consistent Image Generation at High Resolution with Generative Radiance Manifolds—0
GraN-GAN: Piecewise Gradient Normalization for Generative Adversarial Networks—0
Diffusion Probabilistic Model Made Slim—0
CapHDR2IR: Caption-Driven Transfer from Visible Light to Infrared Domain—0
Diffusion Prism: Enhancing Diversity and Morphology Consistency in Mask-to-Image Diffusion—0
CT Reconstruction using Diffusion Posterior Sampling conditioned on a Nonlinear Measurement Model—0
A Picture is Worth a Thousand Words: Principled Recaptioning Improves Image Generation—0
GraPE: A Generate-Plan-Edit Framework for Compositional T2I Synthesis—0
Diffusion on the Probability Simplex—0
Diffusion Motion: Generate Text-Guided 3D Human Motion by Diffusion Model—0
Diffusion Model with Clustering-based Conditioning for Food Image Generation—0
Can We Use Diffusion Probabilistic Models for 3D Motion Prediction?—0
A Picture is Worth a Thousand Prompts? Efficacy of Iterative Human-Driven Prompt Refinement in Image Regeneration Tasks—0
Diffusion Models Without Attention—0
Show:102550
← PrevPage 51 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