AI RESEARCH

DisCa: Accelerating Video Diffusion Transformers with Distillation-Compatible Learnable Feature Caching

arXiv CS.CV

ArXi:2602.05449v3 Announce Type: replace While diffusion models have achieved great success in the field of video generation, this progress is accompanied by a rapidly escalating computational burden. Among the existing acceleration methods, Feature Caching is popular due to its