# Pika-Labs/Pika-H3-Flex

> Pika H3 Flex model for local inference of video generation with synchronized stereo audio in six sampling steps, supporting text, endpoint frames and multimodal references.

- Magnitude: 5.7 out of 10 — Early signal
- Stars: 160 total · +7 stars measured 2026-10-30, 09:22–10:49 UTC, ≈ 49 by evening
- Star trust: star growth looks organic
- Category: Generative media · Language: Python · Created: 2026-10-29 · Last push: 2026-10-29
- GitHub: https://github.com/Pika-Labs/Pika-H3-Flex · Page: https://gitnova.dev/en/r/Pika-Labs/Pika-H3-Flex

## Useful for

- Generate video with synchronized audio from a text prompt locally
- Condition generation on first and last frames to control a shot
- Build reference-guided animation from 9 images, 3 videos and 3 audio clips

## Why it’s here

- Star-counter measurements on 2026-10-30 (UTC), 09:22–10:49: 153 → 160 stars (+7). This is the change over that interval.
- Estimated end-of-day forecast: about +49 stars, using observed gains and the previous day.
- The repository is 1 day old and already has 160 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet.
- Top new repositories this week: #134.
- About 14 forks a day — people are taking the code.
- Recent forks include notable developers: @johndpope (1,333 followers), @mbrukman (399 followers).

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 9
- Issues and pull requests: 0
- Watchers: 0
- Average over the last week: 91 per day
- Usual pace: too little history (under two weeks)
- Stars in the last hour (measured): 5

## Stars per day, last 2 days (oldest → newest, today is partial)

2026-10-29 … 2026-10-30: 132, 7

## Spotted in now

- Top new repositories this week: #134

## More in this category

1. **paipiange/nvzhuang** — 7.9 · Early signal · Generative media · Go · +576 stars measured 2026-10-30, 00:16–10:48 UTC, ≈ 1,011 by evening
   A static catalog of 1407 AI-generated women's clothing images with bilingual search and optional virtual try-on via external image generation models.
   Full card: https://gitnova.dev/en/r/paipiange/nvzhuang.md
2. **anhao/ai-pose-gallery-zh** — 7.1 · Peaking · Generative media · HTML · +537 stars measured 2026-10-30, 00:15–10:48 UTC, ≈ 1,178 by evening
   Chinese localization of an AI pose reference gallery: 1439 records and 2878 images with a ready-to-deploy dependency-free static site. Useful for artists and 3D modelers picking poses.
   Full card: https://gitnova.dev/en/r/anhao/ai-pose-gallery-zh.md
3. **sleepy-zone/ai-ref-library-cn** — 6.7 · Early signal · Generative media · JavaScript · +152 stars measured 2026-10-30, 03:05–10:48 UTC, ≈ 309 by evening
   A Chinese-language search interface for three sets of AI drawing reference materials (faces, poses, clothing) by author agi/gia, with translated tags, bilingual search and one-click prompt copying.
   Full card: https://gitnova.dev/en/r/sleepy-zone/ai-ref-library-cn.md
4. **D3voz/openjutsu** — 6.2 · Early signal · Generative media · TypeScript · +98 stars measured 2026-10-30, 00:16–10:48 UTC, ≈ 221 by evening
   A local web app for swapping characters and objects in videos: drop a video and a character photo, and the main person in the frame is replaced by your character while camera, cuts and soundtrack stay intact. Runs on your own GPU via…
   Full card: https://gitnova.dev/en/r/D3voz/openjutsu.md
5. **OpenSenseNova/SenseNova-6.8-Code2Video** — 5.6 · Early signal · Generative media · Python · +65 stars measured 2026-10-30, 00:17–10:49 UTC, ≈ 128 by evening
   An open lightweight model that creates short videos by generating and rendering executable code, built on Qwen3.8-27B with 512K context. Aimed at researchers exploring programmatic video creation.
   Full card: https://gitnova.dev/en/r/OpenSenseNova/SenseNova-6.8-Code2Video.md

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-10-30 11:02 UTC, updated every 30 minutes.