# FlashML-org/FreeVideo

> A local inference engine for MiniMax H3 video generation on consumer GPUs: runs with as little as 8 GB VRAM and 16 GB RAM, adapting weight placement and precision to the hardware. Ships as a ComfyUI plugin with Windows and macOS launchers.

- Magnitude: 5.4 out of 10 — Early signal
- Stars: 1,150 total · +8 stars measured 2026-10-07, 06:35–08:02 UTC, ≈ 105 by evening
- Star trust: star growth looks organic
- Category: Generative media · Language: Python · License: Apache-2.0 · Created: 2026-09-13 · Last push: 2026-10-07
- GitHub: https://github.com/FlashML-org/FreeVideo · Page: https://gitnova.dev/en/r/FlashML-org/FreeVideo

## Useful for

- Generate a short video from a text prompt on a GPU with 8 GB VRAM
- Install FreeVideo as a custom node in an existing ComfyUI and run the All-in-One template
- Build a video from first and last frames with image or audio references

## Why it’s here

- Star-counter measurements on 2026-10-07 (UTC), 06:35–08:02: 1142 → 1150 stars (+8). This is the change over that interval.
- Estimated end-of-day forecast: about +105 stars, using observed gains and the previous day.
- Over the last two days the pace is 2.2× that of the previous week and a half.
- Elevated gains were measured on the last 3 completed UTC days in a row. Continued growth is not guaranteed.
- The repository is 24 days old and already has 1,150 stars.
- Top new repositories this month: #99.
- About 16 forks a day — people are taking the code.

## 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: 107
- Issues and pull requests: 86
- Watchers: 3
- Average over the last week: 178 per day
- Usual pace: 0 per day
- Stars in the last hour (measured): 6
- Latest release: v0.3.2 (2026-10-07)

## Stars per day, last 25 days (oldest → newest, today is partial)

2026-09-13 … 2026-10-07: 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 168, 309, 309, 142, 214, 8

## Spotted in now

- Top new repositories this month: #99

## Similar by description

1. **killkli/minimax-h3-colab-skill** — 0.7 · Steady · Generative media · Jupyter Notebook · +1 star measured 2026-10-07, 00:29–08:13 UTC, ≈ 2 by evening
   A standalone Codex skill for generating short MiniMax H3 Ref2VA videos from local reference images via Google Colab. It bundles skill instructions, an inference notebook, a Python runner, a shell launcher, and an installer.
   Full card: https://gitnova.dev/en/r/killkli/minimax-h3-colab-skill.md
2. **kandinskylab/kandinsky-6** — 5.4 · Early signal · Generative media · Python · +5 stars measured 2026-10-07, 00:21–08:02 UTC, ≈ 60 by evening
   Kandinsky 6.0 is a family of diffusion models for synchronized text-to-audio-video and image-to-audio-video generation: 5-second clips with 44 kHz audio and lip-sync, upscalable to Full-HD.
   Full card: https://gitnova.dev/en/r/kandinskylab/kandinsky-6.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 2026-10-07 08:16 UTC, updated every 30 minutes.