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 2001–2050 of 6689 papers

TitleStatusHype
StyleShot: A Snapshot on Any StyleCode3
LLM4GEN: Leveraging Semantic Representation of LLMs for Text-to-Image GenerationCode1
BADM: Batch ADMM for Deep Learning—0
InstantStyle-Plus: Style Transfer with Content-Preserving in Text-to-Image GenerationCode2
Chest-Diffusion: A Light-Weight Text-to-Image Model for Report-to-CXR Generation—0
Efficient Personalized Text-to-image Generation by Leveraging Textual SubspaceCode0
Toward a Diffusion-Based Generalist for Dense Vision Tasks—0
The Factuality Tax of Diversity-Intervened Text-to-Image Generation: Benchmark and Fact-Augmented InterventionCode0
Analyzing Quality, Bias, and Performance in Text-to-Image Generative Models—0
Prompt Refinement with Image Pivot for Text-to-Image GenerationCode1
PopAlign: Population-Level Alignment for Fair Text-to-Image GenerationCode0
Wavelets Are All You Need for Autoregressive Image Generation—0
Network Bending of Diffusion Models for Audio-Visual GenerationCode1
MimicMotion: High-Quality Human Motion Video Generation with Confidence-aware Pose GuidanceCode1
Diminishing Stereotype Bias in Image Generation Model using Reinforcemenlent Learning Feedback—0
How Stable is Stable Diffusion under Recursive InPainting (RIP)?—0
DiffLoss: unleashing diffusion model as constraint for training image restoration networkCode0
Rethinking and Defending Protective Perturbation in Personalized Diffusion ModelsCode1
AnyControl: Create Your Artwork with Versatile Control on Text-to-Image GenerationCode2
Structural Attention: Rethinking Transformer for Unpaired Medical Image SynthesisCode1
VDG: Vision-Only Dynamic Gaussian for Driving Simulation—0
MUMU: Bootstrapping Multimodal Image Generation from Text-to-Image Data—0
DiffuseHigh: Training-free Progressive High-Resolution Image Synthesis through Structure GuidanceCode2
MultiDiff: Consistent Novel View Synthesis from a Single Image—0
Q-DiT: Accurate Post-Training Quantization for Diffusion TransformersCode2
SyncNoise: Geometrically Consistent Noise Prediction for Text-based 3D Scene Editing—0
EvolvED: Evolutionary Embeddings to Understand the Generation Process of Diffusion Models—0
Masked Generative Extractor for Synergistic Representation and 3D Generation of Point Clouds—0
TSynD: Targeted Synthetic Data Generation for Enhanced Medical Image Classification—0
FaceScore: Benchmarking and Enhancing Face Quality in Human GenerationCode2
EVALALIGN: Supervised Fine-Tuning Multimodal LLMs with Human-Aligned Data for Evaluating Text-to-Image ModelsCode1
Character-Adapter: Prompt-Guided Region Control for High-Fidelity Character CustomizationCode2
Prompt-Consistency Image Generation (PCIG): A Unified Framework Integrating LLMs, Knowledge Graphs, and Controllable Diffusion ModelsCode0
Repulsive Latent Score Distillation for Solving Inverse ProblemsCode0
ResMaster: Mastering High-Resolution Image Generation via Structural and Fine-Grained Guidance—0
Beyond Thumbs Up/Down: Untangling Challenges of Fine-Grained Feedback for Text-to-Image Generation—0
Repairing Catastrophic-Neglect in Text-to-Image Diffusion Models via Attention-Guided Feature EnhancementCode0
DreamBench++: A Human-Aligned Benchmark for Personalized Image GenerationCode2
EmoAttack: Emotion-to-Image Diffusion Models for Emotional Backdoor Generation—0
Soft Masked Mamba Diffusion Model for CT to MRI ConversionCode2
Disability Representations: Finding Biases in Automatic Image Generation—0
Latent diffusion models for parameterization and data assimilation of facies-based geomodels—0
Backdooring Bias into Text-to-Image ModelsCode0
Holistic Evaluation for Interleaved Text-and-Image Generation—0
Video Generation with Learned Action Prior—0
Invertible Consistency Distillation for Text-Guided Image Editing in Around 7 Steps—0
Consistency Models Made EasyCode3
CollaFuse: Collaborative Diffusion ModelsCode0
Fantastic Copyrighted Beasts and How (Not) to Generate ThemCode1
What's Next? Exploring Utilization, Challenges, and Future Directions of AI-Generated Image Tools in Graphic Design—0
Show:102550
← PrevPage 41 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