CineMaster: A 3D-Aware and Controllable Framework for Cinematic Text-to-Video Generation
Paper
•
2502.08639
•
Published
•
36
Kuaishou Visual Generation and Interaction Center
company
AI & ML interests
KwaiVGI, the innovators behind Kling Video Generation and LivePortrait, explores the cutting-edge technologies of multimedia content creation and interaction. Welcome to join us on this exciting journey to change the world.
Recent Activity
View all activity
KwaiVGI's activity
XintaoÂ
authored
a
paper
8 days ago
liuhuohuoÂ
updated
a
dataset
12 days ago
liuhuohuoÂ
updated
a
model
12 days ago
jieliuÂ
updated
a
Space
12 days ago
jieliuÂ
published
a
Space
13 days ago
liuhuohuoÂ
published
a
model
14 days ago
liuhuohuoÂ
published
a
dataset
14 days ago
liuhuohuoÂ
authored
3
papers
17 days ago
CGB-DM: Content and Graphic Balance Layout Generation with Transformer-based Diffusion Model
Paper
•
2407.15233
•
Published
•
6
Autoregressive Models in Vision: A Survey
Paper
•
2411.05902
•
Published
•
18
Improving Video Generation with Human Feedback
Paper
•
2501.13918
•
Published
•
49
jieliuÂ
authored
a
paper
29 days ago
XintaoÂ
authored
a
paper
29 days ago
lemonaddieÂ
updated
a
dataset
about 1 month ago
lemonaddieÂ
updated
a
model
about 1 month ago
XintaoÂ
authored
a
paper
about 1 month ago
VictorYukiÂ
authored
5
papers
about 1 month ago
Unlimited-Size Diffusion Restoration
Paper
•
2303.00354
•
Published
FreeDoM: Training-Free Energy-Guided Conditional Diffusion Model
Paper
•
2303.09833
•
Published
Neural Video Fields Editing
Paper
•
2312.08882
•
Published
Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Model
Paper
•
2212.00490
•
Published
SkillMimic: Learning Reusable Basketball Skills from Demonstrations
Paper
•
2408.15270
•
Published
•
1