AnyFlow enables any-step video diffusion by distilling flow-map transitions over arbitrary time intervals with on-policy backward simulation.
Phased consistency models.Advances in neural information processing systems, 37:83951–84009, 2024
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.CV 3representative citing papers
Kling-Omni is a unified multimodal generative system that produces cinematic videos from diverse inputs by integrating generation, editing, and intelligent reasoning in a single end-to-end model.
Self-Forcing++ scales autoregressive video diffusion to over 4 minutes by using self-generated segments for guidance, reducing error accumulation and outperforming baselines in fidelity and consistency.
citing papers explorer
-
AnyFlow: Any-Step Video Diffusion Model with On-Policy Flow Map Distillation
AnyFlow enables any-step video diffusion by distilling flow-map transitions over arbitrary time intervals with on-policy backward simulation.
-
Kling-Omni Technical Report
Kling-Omni is a unified multimodal generative system that produces cinematic videos from diverse inputs by integrating generation, editing, and intelligent reasoning in a single end-to-end model.
-
Self-Forcing++: Towards Minute-Scale High-Quality Video Generation
Self-Forcing++ scales autoregressive video diffusion to over 4 minutes by using self-generated segments for guidance, reducing error accumulation and outperforming baselines in fidelity and consistency.