OpenSubject: Leveraging Video-Derived Identity and Diversity Priors for Subject-driven Image Generation and Manipulation
Paper
•
2512.08294
•
Published
•
17
jym
bigmengmeng
·
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
about 1 month ago
OneThinker: All-in-one Reasoning Model for Image and Video
upvoted
a
paper
2 months ago
Think with 3D: Geometric Imagination Grounded Spatial Reasoning from
Limited Views
Organizations
