NVIDIA’s Sol-H3 cuts H3 video generation to four steps
The expensive part of MiniMax-H3 video generation just shrank from 50 scheduler points to four DiT forwards. NVIDIA reports 9.45x to 15.54x lower generation time on one B300, with 10-second, 1344×768 video and native stereo audio produced in 13.745 seconds on a single GPU. The catch: these are B300 benchmarks, and a ComfyUI path still needs to materialize for broader use.