Veda-Sparse/Minimax-H3-T2VA-Veda-8NFE-600Step-Preview · a learned sparse-attention method for video diffusion models. Up to 6.8× attention speedup and 3.1× end-to-end speedup.

⁨3⁩ ⁨likes⁩

Submitted ⁨⁨1⁩ ⁨week⁩ ago⁩ by ⁨Even_Adder@lemmy.dbzer0.com⁩ to ⁨stable_diffusion@lemmy.dbzer0.com⁩

https://huggingface.co/Veda-Sparse/Minimax-H3-T2VA-Veda-8NFE-600Step-Preview

Comments

Sort:hotnew top