Mask$^2$DiT: Dual Mask-based Diffusion Transformer for Multi-Scene Long Video Generation
Paper
•
2503.19881
•
Published
•
6
•
2
Tianhao Qi
qth
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
10 days ago
USO: Unified Style and Subject-Driven Generation via Disentangled and
Reward Learning
commented on
a paper
6 months ago
Mask$^2$DiT: Dual Mask-based Diffusion Transformer for Multi-Scene Long
Video Generation
authored
a paper
6 months ago
DEADiff: An Efficient Stylization Diffusion Model with Disentangled
Representations
Organizations
None yet
commented
a
paper
6 months ago