Pika-Labs/Pika-H3-Flex
Model
Can I trust it?
Be careful with this one.
Warnings Check
Very new: it was created yesterday. Wait a little before installing it.
Stars from real accounts No data
We haven't checked its stars for fakes yet.
Active OK
Last change today.
Licence Careful
No licence: legally you can't reuse the code, unless the README says otherwise.
Quick checks from public data. They help, but they are no guarantee.
What it is
Open-weight video and audio generation model built on MiniMax-H3, producing MP4 video with synchronized stereo audio from text, endpoint frames or multimodal references. Local inference supports native 480p and 768p output; higher resolutions are offered through the hosted Pika…
Who it's for
Creators and developers running local video generation with synchronized audio, and professionals using reference-guided multi-shot workflows
How to use it
Ask your AI to set it up
Paste this into Claude, ChatGPT or your coding assistant.
Help me install and set up Pika-Labs/Pika-H3-Flex in my project. Follow its README: https://github.com/Pika-Labs/Pika-H3-Flex. Explain each step and check it is safe before running anything.
Star curve
On the radar
Its place among the radar's top 100, day by day, with #1 at the top. Gaps are days it was out of the top 100.
Records
- Best place on RepoAlerts: #73, on 30 Oct 2026
Get alerts for repos like this
We'll email you when something in Models & inference starts rising. Free, once a week, only what matches.
What arrives: one email on Mondays with the repos that match, never more. See last week's. Privacy
For maintainers
Add this badge to your README. It shows the repo's place on the radar, updates every hour and links back to this page.
[](https://repoalerts.com/repo/Pika-Labs/Pika-H3-Flex?ref=badge)Similar repos
- code-video-model/CodeVideoModel
A research codebase for generating videos from editable Three.js scenes. It produces Three.js code from text prompts, renders proxy videos, creates reference images, and runs the MiniMax-H3 model to p
- Tencent-Hunyuan/Prism
A research framework for natively training joint video-audio generation models at up to 2K resolution, using dynamic sparse attention. It organizes tokens into spatiotemporal zones and assigns each a
- HKUST-LongGroup/UniAVC
Research code for a unified model that generates joint audio and video from text, performs bidirectional cross-modal synthesis, and edits either or both modalities from an instruction, without task-sp
- PKU-VaLuE-Lab/OmniReasoning
Research code and datasets for OmniReasoning, a framework for audio-visual joint reasoning. It includes the OmniQA data engine that builds reasoning data from videos, the OmniReasoningBench evaluation
- Tencent-Hunyuan/Hy-Nomas
Open-source Python code for Hy-Nomas, an autoregressive video world generation model that produces interactive worlds from free-form text prompts or camera trajectories. The repository provides traini
- apimartchlp3td/minimax-h3-prompts
Documents how to call the MiniMax H3 model (model id MiniMax-H3) through the APIMart OpenAI-compatible video endpoint. Covers request parameters, async task polling, per-second pricing and a Python an