No "Zero-Shot" Without Exponential Data: Pretraining Concept Frequency Determines Multimodal Model Performance Paper • 2404.04125 • Published Apr 4 • 27
CoMat: Aligning Text-to-Image Diffusion Model with Image-to-Text Concept Matching Paper • 2404.03653 • Published Apr 4 • 32
Cross-Attention Makes Inference Cumbersome in Text-to-Image Diffusion Models Paper • 2404.02747 • Published Apr 3 • 11
BeyondScene: Higher-Resolution Human-Centric Scene Generation With Pretrained Diffusion Paper • 2404.04544 • Published Apr 6 • 20
ControlNet++: Improving Conditional Controls with Efficient Consistency Feedback Paper • 2404.07987 • Published Apr 11 • 47
BRAVE: Broadening the visual encoding of vision-language models Paper • 2404.07204 • Published Apr 10 • 15
RealmDreamer: Text-Driven 3D Scene Generation with Inpainting and Depth Diffusion Paper • 2404.07199 • Published Apr 10 • 24
Learning to Route Among Specialized Experts for Zero-Shot Generalization Paper • 2402.05859 • Published Feb 8 • 5
Improving Explicit Spatial Relationships in Text-to-Image Generation through an Automatically Derived Dataset Paper • 2403.00587 • Published Mar 1
FlexCap: Generating Rich, Localized, and Flexible Captions in Images Paper • 2403.12026 • Published Mar 18 • 1
Scaling Rectified Flow Transformers for High-Resolution Image Synthesis Paper • 2403.03206 • Published Mar 5 • 52
Kaleido Diffusion: Improving Conditional Diffusion Models with Autoregressive Latent Modeling Paper • 2405.21048 • Published May 31 • 12