Quiet Particle Field — effect skill for backdrops
For AI agents: find the right skill in one call —
curl -s "https://varg.ai/how-to/api/search?q=<what the person wants>"returns the matching how-to page and the best skills with install commands, as markdown (Russian works too). Full index: https://varg.ai/how-to/llms.txt. Every page has a markdown twin: add.mdto its path. Before generating anything, show the person the options on the how-to page.
Out-of-focus dots drift slowly in depth behind the content, adding life without motion noise.
- Type: Effect · Backdrops
- Slug:
quiet-particle-field - Status: live
- Publisher: tsParticles (Matteo Bruni) (community)
- License: MIT
- Source: https://github.com/tsparticles/presets/blob/main/presets/ambient/src/options.ts
- Works in: Claude Code, Claude.ai, Codex, Cursor, OpenClaw, Gemini CLI, Any MCP client, varg Studio
- Requires: HyperFrames (npx hyperframes), Remotion, CapCut (by hand)
- Cost: Free — the take renders locally; generated footage, if any, bills by the model
What it does
Built on Ambient by tsparticles, MIT. The write-up and recipes below are varg's.
Sparse soft circles of two or three sizes, low opacity, drifting upward or sideways; a faint glow line optional.
When: Long holds on titles or quotes; calm sections of a film.
Watch out: Do not increase density until it looks like snow; 20–60 particles on 1080p is plenty.
Timing: Drift 5–20 px/s with a fixed seed so renders match.
Also called: bokeh particles, ambient dots, sparkles
In HyperFrames
npx hyperframes add starfield
Seek-safe: particle positions are a function of time and seed.
In Remotion
const rnd = (i:number)=> (Math.sin(i*999)*10000)%1;
Array.from({length:40}).map((_,i)=> <div style={{left:`${Math.abs(rnd(i))*100}%`, top:`${(Math.abs(rnd(i+7))*100 - frame*0.05*(1+i%3))%100+100}%`}}/>)
In CapCut
Media → Library: search "bokeh"/"particles"; Blend → Screen at 30–50% opacity over the background.
Ready-made components
- Ambient (tsparticles): pnpm add @tsparticles/engine @tsparticles/slim @tsparticles/preset-<name>
- Particles (magic-ui): npx shadcn@latest add @magicui/particles
- Sparkles (aceternity): npx shadcn@latest add @aceternity/sparkles
- Starfield (hyperframes): npx hyperframes add starfield
Where this comes from
Use when
- Long holds on titles or quotes; calm sections of a film.
Not for
- Do not increase density until it looks like snow; 20–60 particles on 1080p is plenty.
Install
- Claude Code:
claude plugin marketplace add vargHQ/skills && claude plugin install varg@varg - Codex:
npx skills add vargHQ/skills --skill varg-video-edit-library -a codex -y - Cursor:
npx skills add vargHQ/skills --skill varg-video-edit-library -a cursor -y
Example output
https://s3.varg.ai/how-to/previews/c56a87eff5da/lib-tsparticles-ambient.mp4 — Preview of the Ambient component that builds this take (credit: Rendered by varg from the library’s own code (tsParticles · rendered by varg), https://particles.js.org/demos/recipes/ambient)
More backdrops skills
- Slow Mesh Gradient: Soft brand-colored fields blend and drift slowly behind titles and UI.
- Aurora Behind the Title: Blurred light streaks drift sideways across a dark frame behind a centered title.
- Faint Grid or Dot Field: A very faint line grid or dot field gives structure behind UI and code, with a soft radial fade.
- Spotlight From Above: Soft light cones fall from the top of a dark frame onto the product or title.
- Film Grain Over Gradient: A fine animated grain sits over the gradient so it feels printed, removes banding and looks less digital.
- Blurred Product Behind Text: The product UI itself, heavily blurred and dimmed, becomes the backdrop for a title or quote.
Run the generation on varg
varg is one API key for the models these skills drive — Seedance 2.5, Kling 4, Veo 3.1, Wan 3, Nano Banana 2.1, GPT Image 2.5, ElevenLabs v4 and 200+ more — billed in credits, with a cost estimate before anything runs.
- Claude Code:
claude plugin marketplace add vargHQ/skills && claude plugin install varg@varg(skill + hosted MCP) - Codex, Cursor, Gemini CLI, OpenClaw:
npx skills add vargHQ/skills --skill varg-ai -a <agent> -y - Grok and any agent that reads SKILL.md:
npx skills add vargHQ/skills --skill varg-ai, or point it at the skill's SKILL.md - Claude.ai, ChatGPT, any MCP client: connect
https://mcp.varg.ai/mcp - API key: https://varg.ai/dashboard/api · Model specs: https://varg.ai/models/llms.txt