A 5B-parameter video diffusion transformer can be compressed and reformulated as an RNN to generate 5s 480x832 videos on a Snapdragon 8 Gen 5 mobile NPU in about 20 seconds with a VBench score of 83.79.
Lightx2v: Light video generation inference framework.https://github
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
MobileWan: Closing the Quality Gap for Mobile Video Diffusion
A 5B-parameter video diffusion transformer can be compressed and reformulated as an RNN to generate 5s 480x832 videos on a Snapdragon 8 Gen 5 mobile NPU in about 20 seconds with a VBench score of 83.79.