ASCII Humanist Collage — 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.
Old paintings and specimens cut apart and refilled with ASCII, word-fill type and halftone on warm paper.
- Slug:
want-ascii-humanist-collage - Status: wanted
- Publisher: Liam McGregor (community)
- Source: https://x.com/liamjmcgregor/status/2074852273100877962
- Cost: ~35–75 credits / collage (estimate) — Four Nano Banana 2.1 plates at 5.25–15.75 each + four Bria cutouts at ~3 each (catalog of 2026-10-23); public-domain plates cost nothing.
What it does
"Humanist collage": public-domain paintings, engravings and specimens (butterflies, shells, botanicals) are segmented and each region is refilled with ASCII glyph ramps, typewriter word-fill ("CLOUDS / BOAT / OCEAN"), pixel mosaic or halftone, composited on paper and animated with stop-motion jitter into a wordmark reveal. It became the defining design look of mid-2026 once a top AI brand adopted it. An agent sources or generates physical-media plates (GPT Image 2.5 and Nano Banana 2.1 win on paint and engraving textures), cuts subjects with Bria background removal, fills regions in code (textmode.js, the three.js AsciiEffect or a HyperFrames look layer) and animates reveals at 12 fps "on twos".
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/liamjmcgregor/status/2074852273100877962
How an agent would make it: Public-domain or generated plates → segmentation + Bria cutouts → per-region ASCII, word-fill, pixel or halftone fill in code → paper-texture composite → stop-motion reveal in HyperFrames
Models it drives: gpt_image_2_5, nano_banana_2_1, bria_guided_remove_background, render
Example output
https://skills.varg.ai/previews/want-ascii-humanist-collage.webp — A 19th-century-style ship painting whose right half is refilled with typewriter word-fill (BOAT / OCEAN / CLOUDS); one of the Anthropic launch visuals Liam collected and named 'humanist collage' (credit: Anthropic design work, via Liam McGregor (@liamjmcgregor), https://x.com/liamjmcgregor/status/2074852273100877962)
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