Skip to content
伊藤P · 低显存图像生成实测·· 2026-10-08AI score26

MiniMax H3 + Veda image-to-video hands-on test: why 5 minutes became 14 minutes

元画像から動画を作ってみたら、5分が14分になった——MiniMax H3 + Vedaで起きた謎の低速化 → 解決済み

AI briefing

On an RTX 3060 Ti 8GB, generating the source image with Qwen Image 2.1 and then doing a 1376×768 Image to Video of about 5.2 seconds via MiniMax H3 + Veda Sparse Attention took 326.54 seconds the first time, but subsequent runs with the same parameters worsened to 14 minutes 15 seconds.

Open original note.com