PulseAugur
实时 01:30:03
English(EN) minimax h3 is now live on together ai

Together AI 引入 MiniMax H3 全模态视频生成模型

Together AI 已宣布 MiniMax H3 模型可用,这是一个拥有 330 亿参数的全模态视频模型。该模型能够生成从 4 到 15 秒、分辨率高达 2K 的视频片段,并支持原生立体声音频。它可以利用文本、图像、视频和音频作为上下文输入。 AI

影响 使先进的全模态视频生成在 Together AI 平台上可用。

排序理由 该集群描述了在平台上发布特定 AI 模型,属于‘工具’类别,因为它涉及产品/服务的可用性。

在 X — Together (inference / OSS) 阅读 →

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

Together AI 引入 MiniMax H3 全模态视频生成模型

本文如何被排名

Signal score
10 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
该集群描述了在平台上发布特定 AI 模型,属于‘工具’类别,因为它涉及产品/服务的可用性。
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, product
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 — Together (inference / OSS) TIER_1 English(EN) · togethercompute ·

    minimax h3 已在 together ai 上线

    minimax h3 is now live on together ai the 33b omni-modal video model generates 4–15s clips at up to 2k with native stereo audio, using text, images, video + audio as context https://t.co/ZpVoMMx57Y