ViRDM: Controlling Representation Distribution Matching for Few-Step Causal Video Generation
ViRDM speeds causal video generation via a four-step post-training recipe: 84.87 VBench Total, 20 updates, single-GPU support, code, weights, eval.
ViRDM speeds causal video generation via a four-step post-training recipe: 84.87 VBench Total, 20 updates, single-GPU support, code, weights, eval.