PulseAugur
EN
LIVE 14:35:07
中文(ZH) Pika 基于 MiniMax H3 开源 H3 Flex,六步实现音视频联合生成

Pika releases open-source H3 Flex for joint video and audio generation

Pika has released Pika H3 Flex, a derivative model based on MiniMax's H3, offering open-source adapter weights and inference code. This model enables joint generation of video and audio in six steps, supporting various input types for creative tasks like scene design and video editing. Pika H3 Flex achieves high performance and quality, outperforming other open-source video models in benchmarks and demonstrating significant download numbers for its base model, H3. AI

IMPACT Enables creators with new tools for joint video and audio generation, potentially accelerating innovation in AI-powered content creation.

RANK_REASON Release of an open-source derivative model with adapter weights and inference code. [lever_c_demoted from research: ic=1 ai=1.0]

Read on 雷峰网 (Leiphone) →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

Pika releases open-source H3 Flex for joint video and audio generation

How we ranked this

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
Release of an open-source derivative model with adapter weights and inference code. [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, 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
5 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

Full methodology in our editorial standards.

COVERAGE [1]

  1. 雷峰网 (Leiphone) TIER_1 中文(ZH) ·

    Pika Based on MiniMax H3 Open Source H3 Flex, Achieving Audio-Video Joint Generation in Six Steps

    <p style="margin-bottom: 0pt;"><span>近日,Pika 发布 MiniMax H3 衍生模型 Pika H3 Flex,并开放适配器权重与推理代码。该模型通过六步去噪联合生成画面和声音,支持文本、首尾帧和多模态参考输入,供创作者进行镜头设计、参考生成和视频编辑。</span></p><p><span>&nbsp;</span></p><p style="margin-top: 0px; margin-bottom: 0px; text-align: center;"><img border="0" src="https:…