MultiCrafter: High-Fidelity Multi-Subject Generation via Spatially Disentangled Attention and Identity-Aware Reinforcement Learning
Paper
•
2509.21953
•
Published
•
7
Suger
SugerWu
AI & ML interests
None yet
Recent Activity
updated
a dataset
21 days ago
SugerWu/HumanData_Huggingface
upvoted
a
paper
about 2 months ago
PersonaLive! Expressive Portrait Image Animation for Live Streaming
upvoted
a
paper
about 2 months ago
OneStory: Coherent Multi-Shot Video Generation with Adaptive Memory
Organizations
authored
5
papers
4 months ago
CustomCrafter: Customized Video Generation with Preserving Motion and Concept Composition Abilities
Paper
•
2408.13239
•
Published
•
11
VideoMaker: Zero-shot Customized Video Generation with the Inherent Force of Video Diffusion Models
Paper
•
2412.19645
•
Published
•
13
RealCam-I2V: Real-World Image-to-Video Generation with Interactive Complex Camera Control
Paper
•
2502.10059
•
Published
CamI2V: Camera-Controlled Image-to-Video Diffusion Model
Paper
•
2410.15957
•
Published