PulseAugur
实时 00:41:19
Dansk(DA) H3 keeps getting faster. ⚡️

MiniMax H3 视频生成在 Nvidia B200 上实现 2 倍加速

MiniMax AI 宣布其 H3 视频生成模型的速度得到显著提升。使用 SGLang-DiffusionVDN-H3 在八个 Nvidia B200 GPU 上,该系统现在可以在 9.0 秒内生成 14.4 秒的 768p 视频。这代表了实时去噪速度的提升超过两倍,且视频质量没有明显下降。 AI

影响 展示了高效视频生成方面的持续进展,可能降低实时 AI 视频应用的门槛。

排序理由 关于模型性能改进的研究里程碑公告。[lever_c_demoted from research: ic=1 ai=1.0]

在 X — MiniMax AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →

MiniMax H3 视频生成在 Nvidia B200 上实现 2 倍加速

本文如何被排名

Signal score
14 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
关于模型性能改进的研究里程碑公告。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
model release, infra
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准

报道来源 [1]

  1. X — MiniMax AI TIER_1 Dansk(DA) · MiniMax_AI ·

    H3 速度持续提升。⚡️

    H3 keeps getting faster. ⚡️ @sgl_project + VDN-H3 now push MiniMax H3 beyond 2× real-time denoising on 8× B200 - generating 14.4s of 768p video in 9.0s end-to-end after warmup, with no measured quality regression. Open models compound through open ecosystems. 🚀