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 2701–2750 of 6689 papers

TitleStatusHype
Two-stage Cytopathological Image Synthesis for Augmenting Cervical Abnormality Screening—0
Semantic Image Synthesis with Unconditional Generator—0
T-Stitch: Accelerating Sampling in Pre-Trained Diffusion Models with Trajectory StitchingCode2
SRNDiff: Short-term Rainfall Nowcasting with Condition Diffusion ModelCode1
Contrastive Prompts Improve Disentanglement in Text-to-Image Diffusion Models—0
SDXL-Lightning: Progressive Adversarial Diffusion Distillation—0
Layout-to-Image Generation with Localized Descriptions using ControlNet with Cross-Attention Control—0
A User-Friendly Framework for Generating Model-Preferred Prompts in Text-to-Image SynthesisCode0
RealCompo: Balancing Realism and Compositionality Improves Text-to-Image Diffusion ModelsCode2
Visual Style Prompting with Swapping Self-AttentionCode3
CounterCurate: Enhancing Physical and Semantic Visio-Linguistic Compositional Reasoning via Counterfactual ExamplesCode1
On the Semantic Latent Space of Diffusion-Based Text-to-Speech Models—0
The Revolution of Multimodal Large Language Models: A SurveyCode2
Revisiting registration-based synthesis: A focus on unsupervised MR image synthesis—0
Pushing Auto-regressive Models for 3D Shape Generation at Capacity and Scalability—0
DiLightNet: Fine-grained Lighting Control for Diffusion-based Image GenerationCode3
Statistical Test on Diffusion Model-based Anomaly Detection by Selective Inference—0
FiT: Flexible Vision Transformer for Diffusion ModelCode3
UnlearnCanvas: Stylized Image Dataset for Enhanced Machine Unlearning Evaluation in Diffusion ModelsCode2
Visual Concept-driven Image Generation with Text-to-Image Diffusion Model—0
SDiT: Spiking Diffusion Model with Transformer—0
TC-DiffRecon: Texture coordination MRI reconstruction method based on diffusion model and modified MF-UNet methodCode1
The Male CEO and the Female Assistant: Evaluation and Mitigation of Gender Biases in Text-To-Image Generation of Dual Subjects—0
Universal Prompt Optimizer for Safe Text-to-Image GenerationCode0
Training Class-Imbalanced Diffusion Model Via Overlap OptimizationCode0
Fundamental Benefit of Alternating Updates in Minimax OptimizationCode1
UMAIR-FPS: User-aware Multi-modal Animation Illustration Recommendation Fusion with Painting StyleCode0
Exploring Precision and Recall to assess the quality and diversity of LLMsCode0
Generative AI and Process Systems Engineering: The Next Frontier—0
Accelerating Parallel Sampling of Diffusion ModelsCode1
Classification Diffusion Models: Revitalizing Density Ratio Estimation—0
Social Reward: Evaluating and Enhancing Generative AI through Million-User Feedback from an Online Creative CommunityCode1
Textual Localization: Decomposing Multi-concept Images for Subject-Driven Text-to-Image GenerationCode1
Self-Play Fine-Tuning of Diffusion Models for Text-to-Image Generation—0
Adversarial Nibbler: An Open Red-Teaming Method for Identifying Diverse Harms in Text-to-Image GenerationCode1
Magic-Me: Identity-Specific Video Customized DiffusionCode3
L3GO: Language Agents with Chain-of-3D-Thoughts for Generating Unconventional Objects—0
Switch EMA: A Free Lunch for Better Flatness and SharpnessCode1
Towards the Detection of AI-Synthesized Human Face Images—0
Learning Continuous 3D Words for Text-to-Image GenerationCode2
Score-based generative models break the curse of dimensionality in learning a family of sub-Gaussian probability distributions—0
Model Collapse Demystified: The Case of Regression—0
Trustworthy SR: Resolving Ambiguity in Image Super-resolution via Diffusion Models and Human Feedback—0
Disentangled Latent Energy-Based Style Translation: An Image-Level Structural MRI Harmonization Framework—0
Cardiac ultrasound simulation for autonomous ultrasound navigation—0
Collaborative Control for Geometry-Conditioned PBR Image Generation—0
MIGC: Multi-Instance Generation Controller for Text-to-Image SynthesisCode4
CTGAN: Semantic-guided Conditional Texture Generator for 3D Shapes—0
Minecraft-ify: Minecraft Style Image Generation with Text-guided Image Editing for In-Game Application—0
Scalable Diffusion Models with State Space BackboneCode2
Show:102550
← PrevPage 55 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