-
Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction
Paper • 2404.02905 • Published • 71 -
InstantStyle: Free Lunch towards Style-Preserving in Text-to-Image Generation
Paper • 2404.02733 • Published • 23 -
Cross-Attention Makes Inference Cumbersome in Text-to-Image Diffusion Models
Paper • 2404.02747 • Published • 13 -
Bigger is not Always Better: Scaling Properties of Latent Diffusion Models
Paper • 2404.01367 • Published • 23
Chenxin Li
XGGNet
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
5 days ago
OpenThinkIMG: Learning to Think with Images via Visual Tool
Reinforcement Learning
liked
a Space
9 days ago
LYL1015/JarvisIR
liked
a dataset
13 days ago
aadarsh99/kyvo-datasets-and-codebooks
Organizations
None yet
Collections
4
-
Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction
Paper • 2404.02905 • Published • 71 -
InstantStyle: Free Lunch towards Style-Preserving in Text-to-Image Generation
Paper • 2404.02733 • Published • 23 -
Cross-Attention Makes Inference Cumbersome in Text-to-Image Diffusion Models
Paper • 2404.02747 • Published • 13 -
Bigger is not Always Better: Scaling Properties of Latent Diffusion Models
Paper • 2404.01367 • Published • 23
