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

Showing 13011325 of 6689 papers

TitleStatusHype
Energy-Based Cross Attention for Bayesian Context Update in Text-to-Image Diffusion ModelsCode1
Linguistic Binding in Diffusion Models: Enhancing Attribute Correspondence through Attention Map AlignmentCode1
Contrasting Intra-Modal and Ranking Cross-Modal Hard Negatives to Enhance Visio-Linguistic Compositional UnderstandingCode1
Diffusion in Diffusion: Cyclic One-Way Diffusion for Text-Vision-Conditioned GenerationCode1
On the Robustness of Latent Diffusion ModelsCode1
Training-free Diffusion Model Adaptation for Variable-Sized Text-to-Image SynthesisCode1
Norm-guided latent space exploration for text-to-image generationCode1
AI-Generated Image Detection using a Cross-Attention Enhanced Dual-Stream NetworkCode1
Beyond Surface Statistics: Scene Representations in a Latent Diffusion ModelCode1
Rewarded soups: towards Pareto-optimal alignment by interpolating weights fine-tuned on diverse rewardsCode1
On the Difference of BERT-style and CLIP-style Text EncodersCode1
Conditional Diffusion Models for Weakly Supervised Medical Image SegmentationCode1
Microscopy image reconstruction with physics-informed denoising diffusion probabilistic modelCode1
Detector Guidance for Multi-Object Text-to-Image GenerationCode1
An Attentive-based Generative Model for Medical Image SynthesisCode1
The Information Pathways Hypothesis: Transformers are Dynamic Self-EnsemblesCode1
Learning Disentangled Prompts for Compositional Image SynthesisCode1
ReFACT: Updating Text-to-Image Models by Editing the Text EncoderCode1
Image generation with shortest path diffusionCode1
Interactive Character Control with Auto-Regressive Motion Diffusion ModelsCode1
DiffInDScene: Diffusion-based High-Quality 3D Indoor Scene GenerationCode1
Diffusion Self-Guidance for Controllable Image GenerationCode1
Extracting Reward Functions from Diffusion ModelsCode1
Inferring and Leveraging Parts from Object Shape for Improving Semantic Image SynthesisCode1
Nested Diffusion Processes for Anytime Image GenerationCode1
Show:102550
← PrevPage 53 of 268Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Improved DDPMFID12.3Unverified
2ADMFID11.84Unverified
3BigGAN-deepFID8.1Unverified
4Polarity-BigGANFID6.82Unverified
5VQGAN+Transformer (k=mixed, p=1.0, a=0.005)FID6.59Unverified
6MaskGITFID6.18Unverified
7VQGAN+Transformer (k=600, p=1.0, a=0.05)FID5.2Unverified
8CDMFID4.88Unverified
9ADM-GFID4.59Unverified
10RINFID4.51Unverified
#ModelMetricClaimedVerifiedStatus
1PresGANFID52.2Unverified
2RESFLOWFID48.29Unverified
3Residual FlowFID46.37Unverified
4GLF+perceptual loss (ours)FID44.6Unverified
5ProdPoly no activation functionsFID40.45Unverified
6ProdPoly no activation functionsFID36.77Unverified
7ACGANFID35.47Unverified
8DenseFlow-74-10FID34.9Unverified
9NVAE w/ flowFID32.53Unverified
10QSNGANFID31.97Unverified
#ModelMetricClaimedVerifiedStatus
1GLIDE + CLSFID30.87Unverified
2GLIDE + CLIPFID30.46Unverified
3GLIDE + CLS-FREEFID29.22Unverified
4GLIDE + CLIP + CLS + CLS-FREEFID29.18Unverified
5PGMGANFID21.73Unverified
6CLR-GANFID20.27Unverified
7FMFID14.45Unverified
8CT (Direct Generation, NFE=1)FID13Unverified
9CT (Direct Generation, NFE=2)FID11.1Unverified
10GLIDE +CLSKID7.95Unverified