手工川 LogoLovstudio.AI
Lovstudio.AI Skill / Video Creation·VIP · INCLUDED IN MEMBERSHIP

Fourier Portrait

Turn one portrait photo into a vertical short where rotating Fourier circles redraw the whole face, with music, narration and a reveal on the drop

OVERVIEW

What you can do with it

把一张人像照片做成带配乐、旁白、音效和片尾引流的傅里叶本轮绘图竖版短片:旋转圆逐级画出整张脸。 Use when 用户说“用傅里叶画出我的照片”或 “turn my selfie into a Fourier epicycle video”。

Best for
Video Creation
Current version
v0.2.2

BEFORE YOU START

Check that it can run

Runtime
Portable Agent Skills format. Requires uv (or Python 3.10+ with numpy, opencv-python-headless, scipy, skia-python, matplotlib, segno) and ffmpeg/ffprobe. Optional: VOICENGINE_API_KEY (Seed-TTS narration), OPENROUTER_API_KEY (Lyria music), macOS 14+ with Swift (Vision segmentation and face crop).
Dependencies
numpy, opencv-python-headless, scipy, skia-python, matplotlib and segno, resolved by uv from the script header; ffmpeg and ffprobe; PyYAML for the bundled profile and validation scripts
Accounts & keys
Optional: VOICENGINE_API_KEY for Seed-TTS narration and OPENROUTER_API_KEY for Lyria music, read from the environment only. Without them the cut has effects only or uses a supplied track.

No Claude or GPT account? You can still try it: a Skill is not tied to one model vendor. Claude is the most dependable, GPT also works, and with only domestic tools you can start from the WorkBuddy option below, though results may differ.

INSTALLATION

Install it in your AI

Yoda, Codex, Claude Code, and other compatible runtimes use the same Skill. Pick your tool for the exact installation steps.

Save your workspace profile once, and Profile-aware Skills can reuse it at runtime.

Configure profile

INSTALL & CONFIGURE

Yoda

Best when you use several agents: install, assign, and invoke skills from one workspace.

  1. 01Open Skills in Yoda, search for “fourier-portrait”, then select Install on its detail page.
  2. 02In the target agent settings, set the skill to Auto, Manual only, or Off.
  3. 03Reload the current session and choose it from the composer Skill menu. Yoda inserts the native invocation for the active runtime.
Open Yoda

COMPLETE IN YODA

Yoda syncs the installed skill to configured agents, so you do not have to maintain several directories manually.

FIRST INVOCATION

Use lov-fourier-portrait for the following task and validate the result against the skill's acceptance criteria:

Skill declaration: Portable Agent Skills format. Requires uv (or Python 3.10+ with numpy, opencv-python-headless, scipy, skia-python, matplotlib, segno) and ffmpeg/ffprobe. Optional: VOICENGINE_API_KEY (Seed-TTS narration), OPENROUTER_API_KEY (Lyria music), macOS 14+ with Swift (Vision segmentation and face crop).

GUIDE

Use the method

Join VIP to read the complete guide

The full steps, protected materials, and install package are part of Lovstudio VIP, which unlocks every Skill at once.

See Lovstudio VIP

CASES

Used this skill? Share a real result you are happy with, by writing it yourself or asking an agent to prepare it.

Loading cases…

SKILL CARD / TRUST RECORD

See the evidence before you use it

Turns a single-person photo into a publishable vertical Fourier epicycle short: the photo is scanned into glowing line art, rotating circles redraw the whole face as one line while their number grows from 1 to 1024, a slow-motion zoom follows the pen, the reveal lands on the music's drop with a photo / line-art split and the series formula, and an optional card points viewers to a link. Music is generated per film, narration is synthesized with captions, and effects follow the shots.

CARD v0.2.2

Use case

Recreate the rotating-circles portrait clip with the user's own photo, as a ready-to-post short with music, narration and an end card.

Owner · Lovstudio.AI

Skill output

A ready-to-post vertical short plus the line art, contact sheets and a report of errors, sync points, narration timings, loudness and costs.

recognizable facial features in the line art; final reconstruction error under 1 percent; reveal impact on the music drop; each narration line at least 10 dB over music and effects; about -14 LUFS; silent tail under 1 s; text inside the vertical safe areas

Requirements

Optional: VOICENGINE_API_KEY for Seed-TTS narration and OPENROUTER_API_KEY for Lyria music, read from the environment only. Without them the cut has effects only or uses a supplied track.

numpy, opencv-python-headless, scipy, skia-python, matplotlib and segno, resolved by uv from the script header; ffmpeg and ffprobe; PyYAML for the bundled profile and validation scripts

Risks & mitigations

Noisy or low-contrast photos produce blotchy line art and an unrecognizable face. · Render QC stills first, check named facial features, and tune offset, speck size, thin lines and crop before rendering.

+4 more

DIMENSIONS

Dimension map

4 dimensions

Line-art fidelity

The traced line art keeps the person's recognizable features and drops noise.

Two photos of one person: a purple halftone headshot gave 85 clean contours; a dark studio portrait gave 57 after raising the speck threshold, and the thin metal glasses frame was restored by the eye-band top-hat. No second person yet.

Reconstruction accuracy

The epicycle drawing converges to the target path and the reported numbers are real.

Final error 0.16 percent (xy) and 0.33 percent (complex) at N=1024; fitted decay exponents 1.45 and 1.53, close to the 1.45 printed in the reference clip; narration numbers are filled from the same computation.

Production quality

The cut is ready to post: synced, intelligible and within platform norms.

Reveal impact landed on the music drop at 41.5 s by scaling stages 1.126x; every narration line measured 11.4 to 33.0 dB over music and effects after per-line ducking; -14.6 LUFS, true peak -1.5 dBFS, silent tail 0.1 s. No recorded phone-speaker listening test yet.

Render efficiency

Iteration and final renders are fast enough to tune interactively.

QC stills in about 3 seconds; the 54.2-second cut with narration, music and mix in about 62 seconds on Apple silicon; narration is cached per line.

VALUE CARD

Value and delivery boundary

Turn one photo into a ready-to-post Fourier portrait short: scan into line art, staged passes from 1 to 1024 circles, a slow-motion zoom on the pen, a photo / line-art reveal on the music drop, with music, captioned narration, effects and an end card.

Included in Lovstudio VIP

VIP

One price for every VIP Skill

Value anchor

A same-day math-animation short without working out implementations, line-art cleanup, connector strokes, shot design, music sync and narration mixing; outsourced clips of this kind are usually priced per video.

Usage boundary

Covers line art, the Fourier path, cinematic rendering, music generation calls, TTS narration with captions, effects, mixing and the QC report; OpenRouter and Volcengine usage, font and photo rights, cover design and publishing are separate.

Maintenance

Review when skia-python, OpenCV, macOS Vision, Lyria or Seed-TTS interfaces change, and against real use on different people.

Feedback and comments

Login to comment

DISTRIBUTION

Where you can get it

See the real release status for this Skill on each platform. Links open the exact product page when one exists.

LSPublished

Lovstudio.AI

Get, install, and read the guide on Lovstudio.AI.

You are here

WBNot published yet

WorkBuddy

A public listing is not available yet.

The exact product page will appear here after release.

SPNot published yet

Alipay SkillPay

A public listing is not available yet.

The exact product page will appear here after release.

PAIR WITH

Add these capabilities when needed

DETAILS

Permissions and license

Source visibility
Commercial: packages and docs follow entitlement; public product info stays visible.
Data & permissions
A skill may read local files, access the network, or call third-party models. Review its full steps and commands before running.
License
MIT
fourier-seriesepicyclesmath-animationportraitvertical-videosound-design

NEXT STEP

One membership, every Skill.

Return to the catalog and choose by outcome, evidence, and dependencies. With VIP, every Skill installs directly.

Back to current skill results

Lovstudio.AI / KEEP MAKING

The meaning of life is to create.