MIRAGE open-sourced: fixing AI image ripple artifacts from iterative editing
vista8 · x · 2026-09-11
Developer luoxiaoshan, in collaboration with Shanghai Jiao Tong University, released MIRAGE/Mi-Ripple as open source to fix degradation artifacts in iteratively edited AI images.
- The problem: first generations look great, but after 3-4 edit rounds (hair, background, composition), images develop scaly hair, dense repeated grain and fine grid patterns; further edits worsen it, and plain denoising also destroys real detail. Observed on both Image 2.0 and 2.5
- Approach: diagnose the artifact type, then apply precise spectral notch filtering, structure-preserving restoration, or regeneration from a cleaned reference
- Results: visibly reduced grid/scaly/repeated textures while preserving more real detail than naive denoising
- Open-sourced: code, paper, tests, full comparisons, plus an Agent Skill (SKILL.md) defining the full workflow including permission before paid regeneration
More from coding & agent
- Sakana launches Fugu Max and Ultra v2, topping 5 of 8 hard benchmarks via multi-agent orchestration — SakanaAILabs · 2026-09-11
- Cursor Origin repos can now deploy on Netlify, in beta — thisiskp_ · 2026-09-11
- Japanese student's m3e-canvas hits GitHub Trending #1: sketches to AI coding prompts — _AustinCalvert_ · 2026-09-11
- How Turbopack chunks your JavaScript: deep dive into chunking tradeoffs — aidenybai · 2026-09-11
- Open-Source FrameForge Chains MiniMax H3 Generations Into Long Videos on ComfyUI — Super_Range45 · 2026-09-11
- Controlling Home-PC Coding Agents From a Phone With gpt-5.6, Fully Open Source — DRONE_SIC · 2026-09-11