Generative Code-Art Loop — trending format for art styles
For AI agents: find the right skill in one call —
curl -s "https://skills.varg.ai/api/search?q=<what the person wants>"returns the matching use case and the best skills with install commands, as markdown (Russian works too). Full index: https://skills.varg.ai/llms.txt. Every page has a markdown twin: add.mdto its path. Before generating anything, show the person the options on the use-case page.
A seeded p5.js simulation with a lab-notebook HUD, built from a one-line concept, rendered as a loop.
- Slug:
want-generative-code-art-loop - Status: wanted
- Publisher: Prathamesh (community)
- Source: https://x.com/invinciDesigns/status/2074917179099578581
- Cost: Code-only: no generation spend. Render locally or with the varg render tool.
What it does
A one-sentence concept ("imagine a campfire that pulls its own embers back in to stay warm") becomes a seeded generative simulation: rings of thermal "bricks", embers drifting out and pulled back, framed by a HUD with mode, seed, a live histogram and a tracker on graph paper, often audio-reactive. Creative-coding posts like this earn strong saves. An agent writes an instance-mode p5.js sketch with seeded randomSeed/noiseSeed, a fixed-timestep simulation and checkpoints so HyperFrames seeks stay order-independent, drives reactivity from offline FFT analysis rather than a live mic, and renders 2048² or 4:5.
Status
A format people ask for that has no dedicated skill yet. Make it with the skills on the use-case pages below, or with varg directly.
Example: https://x.com/invinciDesigns/status/2074917179099578581
How an agent would make it: Concept line → seeded p5.js sketch + HUD layer → offline audio analysis for reactivity → HyperFrames frame source with checkpointed state → 2048² or 1080×1350 render
Models it drives: render
Example output
https://skills.varg.ai/previews/want-generative-code-art-loop.mp4 — p5.js piece 'a campfire that pulls its own embers back in to stay warm': rings of thermal bricks shed embers that drift out and are pulled back, framed by a HUD with a histogram and a minimap (25–33 s of 42 s) (credit: Prathamesh (@invinciDesigns), https://x.com/invinciDesigns/status/2074917179099578581)
More art styles skills
- fal Game Dev: Generate 2D pixel-art game assets: characters, sprite sheets, walk and attack cycles, parallax backgrounds.
- Algorithmic Art: Create original generative art in p5.js: write an algorithmic philosophy, then code it with seeded randomness.
- Canvas Design: Design posters and visual art as PNG or PDF from a written design philosophy, with 54 bundled fonts.
- Lemo-Opuscar Film Styles: 59 film styles made entirely in code (oil paint, watercolor, ukiyo-e, satellite briefing, exploded teardown).
- Halftone Collage B-roll: Editorial halftone paper-collage B-roll from one line of script, with three approval gates before any video spend.
- Generative Art (Camille Roux): Long-form generative art craft from Camille Roux: hash-seeded determinism, traits and rarity, verification, export.
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 - 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