LinGen replaces self-attention in diffusion transformers with a linear-complexity MATE block, enabling 512p 68-second video generation on a single H100 with quality comparable to Gen-3, LumaLabs, and Kling.
Alabdul- mohsin, et al
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
LinGen: Towards High-Resolution Minute-Length Text-to-Video Generation with Linear Computational Complexity
LinGen replaces self-attention in diffusion transformers with a linear-complexity MATE block, enabling 512p 68-second video generation on a single H100 with quality comparable to Gen-3, LumaLabs, and Kling.