video-watermark-removal
Use when removing a static logo, watermark, or TV bug from a video seamlessly (so it is not noticeable it was ever there). PRIMARY method = ProPainter flow-guided temporal inpaint on a TIGHT logo-only mask (pulls REAL background pixels from neighbouring frames -> sharp, no soft haze), CHUNKED in time so it fits a small GPU and avoids OOM, with PER-FRAME presence gating so frames where the logo is occluded (e.g. a hook card) are left pristine. big-LAMA per-frame is the fast fallback but its fill is visibly SOFT. Plus the pitfalls that actually bite: tight logo-shaped mask not a generous box (oversized boxes smear faces), don't inpaint frames where the logo is absent, chunk long clips to bound RAM, retry transient WSL2 CUDA failures, run as a detached WSL daemon watched by a persistent Monitor, and PROVE clean with a logo-template NCC gate across the whole timeline (never claim done on a single-frame check). Includes a companion method for a FIXED-PATH animated overlay (fades or scrolls along a fixed screen path, identical across many clips) via cross-clip-average phase masks; still NOT for arbitrary moving watermarks or full-frame logos.
- License 许可
- MIT
- 最近更新
- 2026-11-02
- Stars
- ★ 0
- Forks
- 0
01 前言 Front Matter
- name
- video-watermark-removal
- description
- Use when removing a static logo, watermark, or TV bug from a video seamlessly (so it is not noticeable it was ever there). PRIMARY method = ProPainter flow-guided temporal inpaint on a TIGHT logo-only mask (pulls REAL background pixels from neighbouring frames -> sharp, no soft haze), CHUNKED in time so it fits a small GPU and avoids OOM, with PER-FRAME presence gating so frames where the logo is occluded (e.g. a hook card) are left pristine. big-LAMA per-frame is the fast fallback but its fill is visibly SOFT. Plus the pitfalls that actually bite: tight logo-shaped mask not a generous box (oversized boxes smear faces), don't inpaint frames where the logo is absent, chunk long clips to bound RAM, retry transient WSL2 CUDA failures, run as a detached WSL daemon watched by a persistent Monitor, and PROVE clean with a logo-template NCC gate across the whole timeline (never claim done on a single-frame check). Includes a companion method for a FIXED-PATH animated overlay (fades or scrolls along a fixed screen path, identical across many clips) via cross-clip-average phase masks; still NOT for arbitrary moving watermarks or full-frame logos.
02 资源文件 2
- 参考文档provenance/original.SKILL.md17.8 KB
- 参考文档repair.json1.5 KB
03 SKILL.md 正文
Video Watermark / Logo Removal (seamless)
Remove a static, semi-transparent logo/bug from a video so cleanly it is not noticeable it was ever there. Proven on 41 vertical shorts (406x720) end-to-end. The OpusClip-specific instance (watermark spec, download, API) lives in basic-memory: main/projects/reframe/opus-clip-watermark-removal-lama-inpaint-recipe-ops-lessons-.... This skill is the reusable technique.
When to use / when NOT
- USE for: a fixed-position (or slowly-varying) opaque/semi-transparent logo over real content (faces, hair, background), where the area behind it is small and not a critical detail.
- DO NOT use for: moving/animated watermarks (need ProPainter/E2FGVI temporal inpaint), full-frame tiled marks, or marks over fine text you must recover (inpainting invents plausible texture, it cannot recover hidden detail).
Approach decision (pick fast, don't agonize)
ffmpeg delogo— REJECT for anything visible. Interpolates from the box border → a blur patch. Obviously edited.- ProPainter, flow-guided temporal inpaint — PRIMARY (best quality). Even for a STATIC logo, the subject moves slightly, so optical-flow propagation copies the REAL background that was exposed in neighbouring frames into the masked region — actual detail recovery, sharp, no soft haze, no flicker. This is the only thing that produced a truly seamless result on real faces/hair. Run it on a cropped ROI around the logo (e.g. ~280×200) so VRAM is tiny (~1.4 GB on a 6 GB card), and chunk in time (see v4 below) so RAM is bounded.
Pipeline
1. Localize
2. Mask discipline (the part that makes or breaks it)
3. Inpaint one clip
4. Batch + heal transient GPU failures
Pitfalls (all hit in practice)
Secondary / animated overlay marks — the cross-clip-average phase-mask method
QC (do not skip — "seamless" is the whole point)
Env (WSL2 + CUDA, the tested setup)
Reference scripts
04 同仓库更多 Skills
clarify-requirements
Resolve genuine pre-execution ambiguity by scanning repo context, generating 1-6 grounded options, and asking 1-3 focused questions via AskUserQuestion. NOT for mid-task use (injection risk); NOT when the goal is already unambiguous; use to disambiguate vague prompts before any file edits.
openmm-md
Run FREE, open-source, Windows-native GPU molecular dynamics via the openmm-md MCP (OpenMM + CUDA on the local NVIDIA GPU). Use for protein / protein-ligand MD when you want a free stack or are on Windows without a Schrodinger license. Covers the full workflow (prepare, solvate, minimize, equilibrate, production, analyze, mmgbsa) AND an honest decision guide vs Schrodinger Desmond, including how to run Desmond legitimately on Linux or a cloud GPU with a real license. This is a deliberately LESSER free alternative and does NOT replace the schrodinger MCP tools. Do NOT use it to pick a free tool when a validated FEP+, WaterMap, IFD-MD, or Prime MM-GBSA result is actually required.
visual-review
Take screenshots of web pages and UI using Playwright for visual review and iteration
status
Diagnostic status report — shows metaswarm installation state, project setup, and potential issues
start
Use when starting work on any task, when the user mentions metaswarm, or when the user wants to begin tracked development work
setup
Interactive project setup — detects your project, configures metaswarm, writes project-local files