-
FreeNoise: Tuning-Free Longer Video Diffusion Via Noise Rescheduling
Paper • 2310.15169 • Published • 10 -
FreeTraj: Tuning-Free Trajectory Control in Video Diffusion Models
Paper • 2406.16863 • Published • 11 -
CineScale: Free Lunch in High-Resolution Cinematic Visual Generation
Paper • 2508.15774 • Published • 20
Haonan Qiu
MoonQiu
AI & ML interests
None yet
Recent Activity
upvoted a paper about 3 hours ago
World Action Modeling with Progressive Visual Planning upvoted a paper 13 days ago
WorldCrafter: Consistent Video World Model with Implicit 3D-aware Memory upvoted a paper 5 months ago
Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and GenerationOrganizations
-
FreeNoise: Tuning-Free Longer Video Diffusion Via Noise Rescheduling
Paper • 2310.15169 • Published • 10 -
FreeTraj: Tuning-Free Trajectory Control in Video Diffusion Models
Paper • 2406.16863 • Published • 11 -
CineScale: Free Lunch in High-Resolution Cinematic Visual Generation
Paper • 2508.15774 • Published • 20
models 0
None public yet
datasets 0
None public yet