Through-The-Mask: Mask-based Motion Trajectories for Image-to-Video Generation Paper • 2501.03059 • Published 1 day ago • 10
Nested Attention: Semantic-aware Attention Values for Concept Personalization Paper • 2501.01407 • Published 5 days ago • 9
Bringing Objects to Life: 4D generation from 3D objects Paper • 2412.20422 • Published 9 days ago • 32
Add-it: Training-Free Object Insertion in Images With Pretrained Diffusion Models Paper • 2411.07232 • Published Nov 11, 2024 • 63
Improving Visual Commonsense in Language Models via Multiple Image Generation Paper • 2406.13621 • Published Jun 19, 2024 • 13
Make It Count: Text-to-Image Generation with an Accurate Number of Objects Paper • 2406.10210 • Published Jun 14, 2024 • 77