Wedding Immortalist 3D Memory Skill for Muse
Turn wedding photos into an explorable 3D world
- What
- Turn wedding photos into an explorable 3D world
- Cost
- Free
- Needs
- hundreds of wedding photos and/or hours of wedding footage; a GPU machine (or cloud GPU) with Python, COLMAP, and 3D Gaussian Splatting training tooling; storage for trained scenes and galleries. No API keys.
- Install
- Copy the installer prompt below into your Muse — your agent does the rest.
Turns thousands of wedding photos and hours of footage into an immersive 3D Gaussian Splatting experience: it drives the full pipeline from ingestion (photos, video, audio) through COLMAP structure-from-motion and 3DGS training (one scene per venue space, then unified navigation), face detection and clustering (RetinaFace/MTCNN, ArcFace/AdaFace embeddings, HDBSCAN) to build a face-clustered guest roster, AI-curated best-photo selection per person with aesthetic scoring (sharpness, composition, expression, genuine-smile detection), moment detection for a theatre mode where key moments play in-scene as floating video, and a theme-adaptive web viewer whose colors, typography, and UI honor the couple's wedding aesthetic (disco, rustic, beach, modern, queer joy, cultural fusion). Discovered via skills.sh. Honest note: this is an ambitious, compute-heavy pipeline — you will need a GPU, COLMAP, and 3DGS training tooling, plus hundreds of photos and hours of footage for good results; the skill orchestrates and instructs but cannot conjure a 3D scene from a handful of snapshots; anti-patterns section (all-frames extraction, single giant scene, photographer-only sourcing) saves a lot of wasted compute. Trust Hub security checks (Socket, Snyk) pass on skills.sh. Skill Harbor never reviews the code, review it yourself before use. Not verified.
Curated by Skill Harbor — free, open-source skill (MIT) by @curiositech.
Version:
Install
Prerequisites: hundreds of wedding photos and/or hours of wedding footage; a GPU machine (or cloud GPU) with Python, COLMAP, and 3D Gaussian Splatting training tooling; storage for trained scenes and galleries. No API keys. Install "Wedding Immortalist 3D Memory Skill for Muse" for me. Turns wedding photos and video into an immersive 3D Gaussian Splatting experience: COLMAP + 3DGS reconstruction pipeline, face clustering for a guest roster, AI-curated best photos per person with aesthetic scoring, theatre mode with key moments playing in-scene, and a theme-adaptive web viewer. Repository: https://github.com/curiositech/some_claude_skills/blob/main/.claude/skills/wedding-immortalist/SKILL.md 1. Fetch the SKILL.md file from the repository path into a temporary folder and summarize what it does in one or two sentences. 2. Safety check: review the SKILL.md and scripts for anything suspicious (unexpected network calls, shell commands, credential harvesting). This repo should contain zero secrets in code, credentials only via the secure vault, allowed hosts declared in the SKILL.md. Verify that holds here; STOP on any red flag and tell me. 3. Install it as a skill: copy SKILL.md and its helper files into the agent's skills directory, in a folder named "wedding-immortalist". 4. Verify with no network calls: frontmatter valid, files in place. 5. Report what was installed, where, and what I still need to do myself (e.g. gather the photo/video corpus and set up COLMAP + 3DGS training on my GPU machine). GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Never require it unless it's in the prerequisites above. Rules: don't touch anything outside the temp folder and the install target. If anything looks off, stop and ask me.
Questions
How do I install a build?
Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the build up for you — no manual configuration.
Where does my money go?
Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.
What does the ✓ next to a creator’s name mean?
It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a build before installing it.