Frame Guidance: Training-Free Guidance for Frame-Level Control in Video Diffusion Models
Paper
•
2506.07177
•
Published
•
22
Taekyung Ki
taekyungki
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
8 days ago
Visual Diffusion Models are Geometric Solvers
upvoted
a
paper
10 days ago
WithAnyone: Towards Controllable and ID Consistent Image Generation
upvoted
a
paper
10 days ago
VISTA: A Test-Time Self-Improving Video Generation Agent
Organizations
authored
a
paper
5 months ago
authored
3
papers
11 months ago
StyleLipSync: Style-based Personalized Lip-sync Video Generation
Paper
•
2305.00521
•
Published
Learning to Generate Conditional Tri-plane for 3D-aware Expression Controllable Portrait Animation
Paper
•
2404.00636
•
Published
FLOAT: Generative Motion Latent Flow Matching for Audio-driven Talking Portrait
Paper
•
2412.01064
•
Published
•
47