AI Search(@aisearchio):Finally, a speedup method for Minimax H3 reference to video! ComfyUI-Ref2VA-VSA adds video sparse attention to Minimax, generating 5-second clips in ~72s on an RTX 4090. It keeps reference tokens dense while pruning video attention—2.24× faster than VDN-H3 at ~13.5GB VRAM.

AI Search

@aisearchio

Sharing AI stuff 🚀 720K subs Nature lover, PhD, investor, shitposter

加入 February 2023

340 正在关注 23.8K 粉丝

AI Search@aisearchio

2026.09.06 23:41

Finally, a speedup method for Minimax H3 reference to video! ComfyUI-Ref2VA-VSA adds video sparse attention to Minimax, generating 5-second clips in ~72s on an RTX 4090. It keeps reference tokens dense while pruning video attention—2.24× faster than VDN-H3 at ~13.5GB VRAM.

显示更多