Voxel Cartoon Character — trending format for 3D scenes
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 blocky voxel character walks, jumps and lands in a tiny world, rendered from code with no video model.
- Slug:
want-voxel-cartoon-character - Status: wanted
- Publisher: Francesco (community)
- Source: https://x.com/francescoinweb3/status/2113585622317244526
- Cost: The code route has no generation spend; the generative route uses MiniMax H3 Max Low Poly (priced per clip in the varg catalog).
What it does
Blocky voxel characters idle, crouch, jump and land on floating grass-and-dirt islands, with flat colors or soft depth of field. The founder's board saved a blocky-character jump clip (origin unknown); this October post shows the same idea agent-made, a voxel mascot walking through six rooms where "no video model made a single frame". An agent builds instanced-cube scenes in three.js, rigs characters (skinview3d ships walk, run, fly and swim clips plus custom animations), scripts camera moves through a HyperFrames frame source, or takes the generative route with MiniMax H3 Max Low Poly; looping parkour runs double as backgrounds for chat stories.
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/francescoinweb3/status/2113585622317244526
How an agent would make it: Voxel scene (three.js instanced cubes) + rigged blocky character → animation clips (idle, walk, jump) → scripted camera → HyperFrames or Remotion render; generative route: MiniMax H3 Max Low Poly
Models it drives: minimax_h3_max_style_low_poly, minimax_h3_max_3d_to_video, render
Example output
https://skills.varg.ai/previews/want-voxel-cartoon-character.mp4 — A blocky red voxel character with soft depth of field hops and waves through 'rooms' of a code-built studio video (Remotion, no video model), shown inside his studio UI (11.5–19.5 s of 24 s) (credit: Francesco (@francescoinweb3), https://x.com/francescoinweb3/status/2113585622317244526)
More 3D scenes skills
- Three.js Skills: 13 Three.js skills: scenes, geometry, materials, lighting, GLSL and TSL shaders, animation, post-processing, R3F.
- Three.js Scene Composition: Plan, build and capture Three.js scenes for video: absolute-time frames, seeded motion, color-safe glTF, render QA.
- R3F Skills: 11 React Three Fiber skills checked against Fiber 9.7 and three r185: Canvas, demand loops, loaders, shaders, post.
- Procedural 3D Story: Turn a myth or book into a seeded, multi-chapter procedural three.js film in one scene.html, audited frame by frame.
- Three.js Architecture Effects: Self-assembling 3D buildings in three.js: bricks, timber, eaves and PBR, driven by one seekable progress value.
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