NVIDIA turns distillation into pluggable LoRAs: train once, then deploy to 54 video models without retraining
LongLive-Plug introduces a once-for-all distillation framework that distills single-pass classifier-free guidance, four-step sampling, and long-context error correction into reusable LoRAs on a base model, enabling training-free plug-and-play deployment to 54 downstream video models across three backbone families, with results on SCOPE and Wan2.2-Fun-5B-Control that beat naive four-step sampling and approach per-target distillation.