OpenVDN/vdn-minimax-h3: Hybrid Attention to Speed Up Video Models with Near-Lossless Quality

Submitted ⁨⁨2⁩ ⁨weeks⁩ ago⁩ by ⁨Even_Adder@lemmy.dbzer0.com⁩ to ⁨stable_diffusion@lemmy.dbzer0.com⁩

https://github.com/OpenVDN/vdn-minimax-h3