Causal Diffusion Transformers for Generative Modeling
Paper • 2412.12095 • Published • 23
Image Generation
Image Generation
-
-
SnapGen: Taming High-Resolution Text-to-Image Models for Mobile Devices with Efficient Architectures and Training
Paper • 2412.09619 • Published • 32 -
DiffSensei: Bridging Multi-Modal LLMs and Diffusion Models for Customized Manga Generation
Paper • 2412.07589 • Published • 48 -
Flowing from Words to Pixels: A Framework for Cross-Modality Evolution
Paper • 2412.15213 • Published • 28 -
CLEAR: Conv-Like Linearization Revs Pre-Trained Diffusion Transformers Up
Paper • 2412.16112 • Published • 23 -
Parallelized Autoregressive Visual Generation
Paper • 2412.15119 • Published • 53 -
Democratizing Text-to-Image Masked Generative Models with Compact Text-Aware One-Dimensional Tokens
Paper • 2501.07730 • Published • 18 -
SANA 1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion Transformer
Paper • 2501.18427 • Published • 27 -
Improved Training Technique for Latent Consistency Models
Paper • 2502.01441 • Published • 8 -
I Think, Therefore I Diffuse: Enabling Multimodal In-Context Reasoning in Diffusion Models
Paper • 2502.10458 • Published • 38 -
EQ-VAE: Equivariance Regularized Latent Space for Improved Generative Image Modeling
Paper • 2502.09509 • Published • 9 -
LDGen: Enhancing Text-to-Image Synthesis via Large Language Model-Driven Language Representation
Paper • 2502.18302 • Published • 5 -
How far can we go with ImageNet for Text-to-Image generation?
Paper • 2502.21318 • Published • 26 -
RectifiedHR: Enable Efficient High-Resolution Image Generation via Energy Rectification
Paper • 2503.02537 • Published • 12 -
Inductive Moment Matching
Paper • 2503.07565 • Published • 6 -
Autoregressive Image Generation with Randomized Parallel Decoding
Paper • 2503.10568 • Published • 9 -
DiT-Air: Revisiting the Efficiency of Diffusion Model Architecture Design in Text to Image Generation
Paper • 2503.10618 • Published • 19 -
Neighboring Autoregressive Modeling for Efficient Visual Generation
Paper • 2503.10696 • Published • 8 -
Tokenize Image as a Set
Paper • 2503.16425 • Published • 16 -
Ultra-Resolution Adaptation with Ease
Paper • 2503.16322 • Published • 13 -
When Less is Enough: Adaptive Token Reduction for Efficient Image Representation
Paper • 2503.16660 • Published • 73 -
Equivariant Image Modeling
Paper • 2503.18948 • Published • 15 -
Diffusion-4K: Ultra-High-Resolution Image Synthesis with Latent Diffusion Models
Paper • 2503.18352 • Published • 7 -
TextCrafter: Accurately Rendering Multiple Texts in Complex Visual Scenes
Paper • 2503.23461 • Published • 94 -
HiFlow: Training-free High-Resolution Image Generation with Flow-Aligned Guidance
Paper • 2504.06232 • Published • 13 -
VisualCloze: A Universal Image Generation Framework via Visual In-Context Learning
Paper • 2504.07960 • Published • 50 -
PixelFlow: Pixel-Space Generative Models with Flow
Paper • 2504.07963 • Published • 18 -
GigaTok: Scaling Visual Tokenizers to 3 Billion Parameters for Autoregressive Image Generation
Paper • 2504.08736 • Published • 46 -
SimpleAR: Pushing the Frontier of Autoregressive Visual Generation through Pretraining, SFT, and RL
Paper • 2504.11455 • Published • 14 -
REPA-E: Unlocking VAE for End-to-End Tuning with Latent Diffusion Transformers
Paper • 2504.10483 • Published • 22 -
T2I-R1: Reinforcing Image Generation with Collaborative Semantic-level and Token-level CoT
Paper • 2505.00703 • Published • 44 -
End-to-End Vision Tokenizer Tuning
Paper • 2505.10562 • Published • 22 -
STARFlow: Scaling Latent Normalizing Flows for High-resolution Image Synthesis
Paper • 2506.06276 • Published • 27 -
Improving Progressive Generation with Decomposable Flow Matching
Paper • 2506.19839 • Published • 8 -
Qwen-Image Technical Report
Paper • 2508.02324 • Published • 276 -
PixNerd: Pixel Neural Field Diffusion
Paper • 2507.23268 • Published • 52 -
DiT360: High-Fidelity Panoramic Image Generation via Hybrid Training
Paper • 2510.11712 • Published • 31 -
Generating an Image From 1,000 Words: Enhancing Text-to-Image With Structured Captions
Paper • 2511.06876 • Published • 28 -
FARMER: Flow AutoRegressive Transformer over Pixels
Paper • 2510.23588 • Published • 59 -
Kandinsky 5.0: A Family of Foundation Models for Image and Video Generation
Paper • 2511.14993 • Published • 234 -
DeCo: Frequency-Decoupled Pixel Diffusion for End-to-End Image Generation
Paper • 2511.19365 • Published • 66 -
Terminal Velocity Matching
Paper • 2511.19797 • Published • 12 -
OmniAlpha: A Sequence-to-Sequence Framework for Unified Multi-Task RGBA Generation
Paper • 2511.20211 • Published • 12 -
PixelGen: Pixel Diffusion Beats Latent Diffusion with Perceptual Loss
Paper • 2602.02493 • Published • 46 -
Image Generation with a Sphere Encoder
Paper • 2602.15030 • Published • 20 -
RAISE: Requirement-Adaptive Evolutionary Refinement for Training-Free Text-to-Image Alignment
Paper • 2603.00483 • Published • 3 -
DREAM: Where Visual Understanding Meets Text-to-Image Generation
Paper • 2603.02667 • Published • 6 -
OmniLottie: Generating Vector Animations via Parameterized Lottie Tokens
Paper • 2603.02138 • Published • 151 -
Spectrum Matching: a Unified Perspective for Superior Diffusability in Latent Diffusion
Paper • 2603.14645 • Published • 5 -
Rethinking UMM Visual Generation: Masked Modeling for Efficient Image-Only Pre-training
Paper • 2603.16139 • Published • 33 -
Representation Alignment for Just Image Transformers is not Easier than You Think
Paper • 2603.14366 • Published • 13 -
Unify-Agent: A Unified Multimodal Agent for World-Grounded Image Synthesis
Paper • 2603.29620 • Published • 49 -
FlowInOne:Unifying Multimodal Generation as Image-in, Image-out Flow Matching
Paper • 2604.06757 • Published • 10