MoCha-LD: Temporal-Chunked Latent Diffusion with Motion-Aware Consistency Regularization for Long Video Generation

Fuente: Zenodo

Saved in:

Bibliographic Details
Main Author:	Jin, Haopeng
Format:	Recurso digital
Language:	English
Published:	Zenodo 2026
Subjects:	MoCha-LD Latent Temporal Chunk Diffusion Overlap Boundary Stitching Memory-Conditioned Cross-Chunk Denoising Motion-Aware Latent Warping Consistency Velocity-Field Agreement Regularization Hierarchical Training Curriculum Video LDM Make-A-Video Imagen Video machine learning deep learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Description not available.

Similar Items