# harry7557558/spirula-studio

> A self-contained C++ binary for training 3D Gaussian Splatting models: turns photos and video into splats and textured meshes, running on NVIDIA, AMD, Intel and Apple GPUs via Vulkan or CUDA without Python or COLMAP.

- Magnitude: 2.0 out of 10 — Steady
- Stars: 2,102 total · +8 stars measured 2026-11-03, 00:36–17:20 UTC, ≈ 12 by evening
- Star trust: star growth looks organic
- Category: Generative media · Language: C++ · License: GPL-3.0 · Created: 2024-05-04 · Last push: 2026-11-01
- GitHub: https://github.com/harry7557558/spirula-studio · Page: https://gitnova.dev/en/r/harry7557558/spirula-studio

## Useful for

- Train a 3DGS model from video on an AMD or Intel GPU without CUDA
- Build a textured mesh from 360-camera panoramas without undistortion
- Run training on a remote GPU via CLI and watch progress in the browser

## Why it’s here

- Star-counter measurements on 2026-11-03 (UTC), 00:36–17:20: 2094 → 2102 stars (+8). This is the change over that interval.
- Estimated end-of-day forecast: about +12 stars, using observed gains and the previous day.
- Recent forks include notable developers: @vaimalaviya1233 (579 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: 202
- Issues and pull requests: 304
- Watchers: 38
- Average over the last week: 20 per day
- Usual pace: 25 per day
- Stars in the last hour (measured): 0
- Latest release: v2026.10.30 (2026-10-30)

## Stars per day, last 30 days (oldest → newest, today is partial)

2026-10-05 … 2026-11-03: 22, 36, 17, 34, 34, 22, 22, 16, 17, 17, 34, 29, 21, 19, 20, 20, 19, 19, 14, 8, 31, 42, 35, 31, 23, 23, 13, 21, 19, 8

## Magnitude by day, last 14 days

10-17 2.1, 10-18 1.9, 10-19 1.9, 10-20 1.8, 10-21 1.7, 10-26 2.1, 10-27 2.6, 10-28 2.5, 10-29 2.3, 10-30 2.1, 10-31 1.9, 11-01 1.9, 11-02 2.2, 11-03 2.1

## Hacker News

- Spirula-studio: 3D Gaussian Splatting trainer video to splat to mesh — 5 points, 0 comments: https://news.ycombinator.com/item?id=49895287

## More in this category

1. **mromidev/claude-animated-shorts** — 7.5 · Early signal · Generative media · TypeScript · +447 stars measured 2026-11-03, 00:30–17:10 UTC, ≈ 609 by evening
   A free Claude skill that produces 55-70 second vertical animated story shorts with 2D characters in a 3D world, rendered locally via three.js inside Remotion without an AI video generator.
   Full card: https://gitnova.dev/en/r/mromidev/claude-animated-shorts.md
2. **hongye007/open-pose-costume** — 6.6 · Early signal · Generative media · TypeScript · +269 stars measured 2026-11-03, 00:31–17:10 UTC, ≈ 357 by evening
   A bilingual reference studio with 5,855 pose, costume, and character references for character design, drawing practice, and AI generation. It lets you search and combine references, then generate a character image via a configured image…
   Full card: https://gitnova.dev/en/r/hongye007/open-pose-costume.md
3. **Pika-Labs/Pika-H3-Flex** — 6.2 · Early signal · Generative media · Python · +535 stars measured 2026-11-03, 00:31–17:10 UTC, ≈ 698 by evening
   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.
   Full card: https://gitnova.dev/en/r/Pika-Labs/Pika-H3-Flex.md
4. **anhao/ai-pose-gallery-zh** — 5.8 · Cooling · Generative media · TypeScript · +275 stars measured 2026-11-03, 00:31–17:10 UTC, ≈ 374 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
5. **D3voz/openjutsu** — 5.5 · Early signal · Generative media · TypeScript · +145 stars measured 2026-11-03, 00:31–17:11 UTC, ≈ 198 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

---

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 2026-11-03 17:28 UTC, updated every 30 minutes.