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 2301–2350 of 6689 papers

TitleStatusHype
Improving Compositional Generation with Diffusion Models Using Lift ScoresCode0
Higher fidelity perceptual image and video compression with a latent conditioned residual denoising diffusion modelCode0
Safe-Sora: Safe Text-to-Video Generation via Graphical Watermarking—0
Few-Shot Concept Unlearning with Low Rank Adaptation—0
Guiding Diffusion with Deep Geometric Moments: Balancing Fidelity and Variation—0
Model alignment using inter-modal bridges—0
Context-Aware Autoregressive Models for Multi-Conditional Image Generation—0
Exploring Sparsity for Parameter Efficient Fine Tuning Using WaveletsCode0
Measurement Score-Based Diffusion ModelCode0
DRAGON: A Large-Scale Dataset of Realistic Images Generated by Diffusion Models—0
PSDiffusion: Harmonized Multi-Layer Image Generation via Layout and Appearance Alignment—0
CompAlign: Improving Compositional Text-to-Image Generation with a Complex Benchmark and Fine-Grained Feedback—0
HSRMamba: Efficient Wavelet Stripe State Space Model for Hyperspectral Image Super-ResolutionCode0
DDAE++: Enhancing Diffusion Models Towards Unified Generative and Discriminative Learning—0
Generative Models in Computational Pathology: A Comprehensive Survey on Methods, Applications, and Challenges—0
Shackled Dancing: A Bit-Locked Diffusion Algorithm for Lossless and Controllable Image Steganography—0
LoFT: LoRA-fused Training Dataset Generation with Few-shot GuidanceCode0
IMAGE-ALCHEMY: Advancing subject fidelity in personalised text-to-image generation—0
End-to-End Vision Tokenizer Tuning—0
Don't Forget your Inverse DDIM for Image Editing—0
An Initial Exploration of Default Images in Text-to-Image Generation—0
EnerVerse-AC: Envisioning Embodied Environments with Action Condition—0
Skeleton-Guided Diffusion Model for Accurate Foot X-ray Synthesis in Hallux Valgus DiagnosisCode0
Selftok: Discrete Visual Tokens of Autoregression, by Diffusion, and for Reasoning—0
Metrics that matter: Evaluating image quality metrics for medical image generationCode0
Towards SFW sampling for diffusion models via external conditioningCode0
Image-Guided Microstructure Optimization using Diffusion Models: Validated with Li-Mn-rich Cathode Precursors—0
Replay-Based Continual Learning with Dual-Layered Distillation and a Streamlined U-Net for Efficient Text-to-Image Generation—0
HCMA: Hierarchical Cross-model Alignment for Grounded Text-to-Image GenerationCode0
Learning Graph Representation of Agent DiffusersCode0
PIDiff: Image Customization for Personalized Identities with Diffusion Models—0
Mogao: An Omni Foundation Model for Interleaved Multi-Modal Generation—0
Does CLIP perceive art the same way we do?—0
Normalize Everything: A Preconditioned Magnitude-Preserving Architecture for Diffusion-Based Speech Enhancement—0
Prompt to Polyp: Medical Text-Conditioned Image Synthesis with Diffusion ModelsCode0
ViCTr: Vital Consistency Transfer for Pathology Aware Image Synthesis—0
Efficient Flow Matching using Latent Variables—0
Defining and Quantifying Creative Behavior in Popular Image Generators—0
MAISY: Motion-Aware Image SYnthesis for Medical Image Motion Correction—0
Unmasking the Canvas: A Dynamic Benchmark for Image Generation Jailbreaking and LLM Content Safety—0
CRAFT: Cultural Russian-Oriented Dataset Adaptation for Focused Text-to-Image Generation—0
CountDiffusion: Text-to-Image Synthesis with Training-Free Counting-Guidance Diffusion—0
Lay-Your-Scene: Natural Scene Layout Generation with Diffusion Transformers—0
Real-Time Person Image Synthesis Using a Flow Matching ModelCode0
Distribution-Conditional Generation: From Class Distribution to Creative Generation—0
Safer Prompts: Reducing IP Risk in Visual Generative AI—0
Preliminary Explorations with GPT-4o(mni) Native Image Generation—0
Multimodal Benchmarking and Recommendation of Text-to-Image Generation ModelsCode0
MCCD: Multi-Agent Collaboration-based Compositional Diffusion for Complex Text-to-Image Generation—0
Text to Image Generation and Editing: A Survey—0
Show:102550
← PrevPage 47 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