# miyang-ai/Mi-Ripple

> Reference implementation of Mi-Ripple, a diagnosis-guided pipeline for restoring AI images that picked up grid-like and scale-like artifacts during iterative editing. It separates periodic lattice artifacts, granular noise in flat regions, and content-entangled artifacts, and requires human review in ambiguous cases.

- Magnitude: 1.1 out of 10 — Steady
- Stars: 177 total · +0 stars on 2026-09-27 (UTC), ≈ 7 by evening
- Star trust: star growth looks organic
- Category: Generative media · Language: Python · License: MIT · Created: 2026-09-10 · Last push: 2026-09-10
- GitHub: https://github.com/miyang-ai/Mi-Ripple · Homepage: https://lab.miyang.cn/ripple/ · Page: https://gitnova.dev/en/r/miyang-ai/Mi-Ripple

## Useful for

- Run mi-ripple on an image to get a diagnosis JSON, masks, and a final picture
- Inspect the generated heat maps and comparison boards before accepting output
- Trigger optional regeneration with --allow-regen and a MIYANG API key after manual approval

## Why it’s here

- 0 stars so far today, about 7 expected by the end of the day.
- The repository is 17 days old and already has 177 stars.

## 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: 6
- Issues and pull requests: 1
- Watchers: 1
- Average over the last week: 10 per day
- Usual pace: 6 per day

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

2026-10-04 … 2026-11-02: None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None

## Magnitude by day, last 13 days

09-15 1.2, 09-16 1.1, 09-17 1.1, 09-18 1.1, 09-19 1.3, 09-20 1.6, 09-21 1.5, 09-22 1.4, 09-23 1.3, 09-24 1.5, 09-25 1.3, 09-26 1.3, 09-27 1.1

---

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 2026-09-27 00:15 UTC, updated every 30 minutes.