Footer

Your go-to destination for discovering trending open-source projects and uncovering the insights that matter

Legal

  • Terms and conditions
  • Privacy policy

More

  • Pricing
  • Advertise
  • onedump
  • gosnakego
  • Contact us

Social

  • X (Twitter)
  • GitHub
Trendshift owl
What they build speaks louder than words
© 2026 Trendshift, created by Julian Li with ❤️
SignalAdvertise
Trendshift
SignalAdvertise
Sign in
Trendshift owl

Discover trends that matter

SignalAdvertise
DailyWeeklyMonthlyYearly
Live mentionsTopics
RepositoriesDevelopers
InsightsStats

Bifrost
Bifrost

Pika-Labs/Pika-H3-Flex

Pika H3 Flex: video and audio generation inference

#AI video generation
Visit GitHub
Python
1.6k
31
1 contributors
Custom license
FeaturedAdvertise to 180K+ monthly visitors
Bifrost

Fastest Enterprise AI Gateway for Routing, Governing, and Securing all your AI Traffic

Momentum

How fast Pika-Labs/Pika-H3-Flex is gaining stars, and where it lands on Trendshift and GitHub Trending

Activity and trending

Stars, forks and merged pull requests each day or month, lined up with the repository's rank on Trendshift Trending

Oct 29 – Nov 4, 2026

Stars +1,495 in 7 days

05001K
684

Forks +31 in 7 days

0510
9

Merged PRs 0 in 7 days

01

Trendshift Trendingwhere the repository ranked each day it made the top 25

Not in the Trendshift top 25 in this period

Oct 29Oct 30Oct 31Nov 1Nov 2Nov 3Nov 4
The left and right arrow keys step from day to day; Home and End go to the first and the last

Stars, forks, merged pull requests and Trendshift Trending rank, by day
DayStars gainedForks gainedMerged PRs
Thu, Oct 29, 2026+0+30
Fri, Oct 30, 2026+120+90
Sat, Oct 31, 2026+51+30
Sun, Nov 1, 2026+110+70
Mon, Nov 2, 2026+217+10
Tue, Nov 3, 2026+684+50
Wed, Nov 4, 2026+313+30
Total+1,495+310
  • 1#1 on the list
  • 7Rank that day
  • Not trending

Social mentions

Recent discussions about this repository across the web
  1. Nov 41 post
    • 4 GitHub breakouts from this week — and none of them is a new model: 1️⃣ agent-autoloop — lets your CLI coding agent (Claude Code, Codex) run in the background, pick up work itself and follow it…

      Read full on X, posted by @WuRichard_

      @WuRichard_ · x.com

  2. Nov 31 post
    • 这两天在玩 Pika H3 Flex 生成视频 出片速度比之前肉眼可见快了 于是让鲸鱼娘和 Claude 小克飙了段戏 画面我觉得很不错了 但原生配音有点拉胯 台词字幕偶尔错位 连音色都不太稳 反手用蚂蚁百灵开源的 Ming-3.0-TTS 重刷了八句台词 这版就舒服多了😎 Pika H3 Flex 实测数据 & 下载地址 ⬇️ #DeepSeek #Ming #tts #h3

      Read full on X, posted by @FiniYang

      @FiniYang · x.com

  3. Nov 11 post
    • 最近有个在 MiniMax H3 上后训练的开源 LoRA 挺火 我在 RTX 4080 上实测了下 上面是原版 20 步,下面是 加了 Pika-H3-Flex 的 6 步 提示词和种子都一样,1280×736,5 秒 原版跑了 475 秒,Flex 162 秒,快了差不多 3 倍。重点是 Flex 的画质和剧情也更好 后来我又试了下写实和古风剧情:…

      Read full on X, posted by @eternityspring

      @eternityspring · x.com

  4. Oct 302 posts4 posts
    • Pika 开源了 H3 Flex:6 步生成带同步立体声的视频,最多能喂 12 个参考素材(9 张图、3 段视频、3 段音频)。 本地原生 480p / 768p,要 1080p 到 4K 得走 Pika 的托管 API。 可惜门槛有点高

      Read full on X, posted by @mi_kuai_rai

      @mi_kuai_rai · x.com

    • 做视频的人最烦什么?改一版等半天。Pika 刚开源的 H3 Flex 就是冲着这个来的:采样步数从 50 步压到 6 步,15 秒带同步音频的 768p 片子,transformer 计算只要 7 秒——先说清楚:7 秒是计算时间(受控基准),不是端到端。 它是 MiniMax H3 后训练来的(33B),最多 12 个参考(图、视频、音频都能往里塞),本地能出…

      Read full on X, posted by @LJL06019

      @LJL06019 · x.com

    • Pika 原文翻译:H3 Flex 首发登上 DesignArena 文生视频榜开放权重模型第一。面向专业迭代,支持导出分离音轨、最高 4K,生成快于实时:带配乐的 15 秒视频最快 7 秒。官方称“有点秀”。 Pika 另称基于 MiniMax H3 后训练,已开放代码和权重。7 秒是官方声明,硬件与条件待核对,不能当作单卡实测。

      Read full on X, posted by @ShenfuX

      @ShenfuX · x.com

    • The Pika team post-trained @MiniMax_AI’s H3 model, giving creators the speed, flexibility, and precision to explore new ideas. The @neobrowser content team can’t wait to put it to work.

      Read full on X, posted by @H0wie_Xu

      @H0wie_Xu · x.com

You might also like

Repositories close to Pika-Labs/Pika-H3-Flex
FeaturedAdvertise to 180K+ monthly visitors
Bifrost

Fastest Enterprise AI Gateway for Routing, Governing, and Securing all your AI Traffic

SamurAIGPT/flux-3-video-api

Python

Python wrapper for Black Forest Labs' FLUX 3 video API — Text-to-Video and Image-to-Video with native synchronized audio.

9812

shengshu-ai/vidu-skills

vidu video generation skills

7928

SkyworkAI/SkyReels-V3

Python

SkyReels V3: Multimodal Video Generation Model

59498

Anil-matcha/MiniMax-H3-API

Python

Python SDK for the MiniMax H3 API — text-to-video, image-to-video, and first/last-frame video generation via Muapi.

5611

302ai/302_video_generator

TypeScript

🎬🤖 302 AI Video Generator! 🚀✨

11336

Anil-matcha/Wan-3.0-API

Python

Wan 3.0 API Python SDK and MCP server for AI video generation: text-to-video, image-to-video, multimodal references, uploads, and async job polling.

8010

zhouwei713/seedance-prompt

Hermes skill for realistic AI video prompts for Seedance and text-to-video models.

33559

agent-next/video-agent

Python

Open-source video generation — Ollama for MiniMax H3. Local director on ComfyUI.

1175

kandinskylab/kandinsky-6

Python

Kandinsky 6.0 Video: Foundation Models for Synchronized Video and Audio Generation

35433