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
upvoted
a
paper
9 days ago
Stroke3D: Lifting 2D strokes into rigged 3D model via latent diffusion models
upvoted
a
paper
17 days ago
PixelGen: Pixel Diffusion Beats Latent Diffusion with Perceptual Loss
updated
a dataset
about 1 month ago
SugerWu/HumanData_Huggingface
Organizations
authored
5
papers
5 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