Procedural 3D geometry, GLSL noise art, and AI-parameter-driven generative systems in React Three Fiber
The AI-Driven Generative 3D Art Engine is the framework for developers and artists building the intersection of artificial intelligence and generative 3D art. Every prompt in this framework is designed around the idea that AI is not just a code generator — it is a creative parameter space. The framework covers procedural geometry systems (L-systems for organic growth, subdivision surfaces for smooth organic forms, parametric meshes for mathematical art), GLSL generative shaders (reaction-diffusion for organic patterns, Voronoi growth for cellular structures), and the AI parameter mapping system that lets an LLM generate seed values that drive the entire generative system — creating unique, reproducible artworks from text prompts. Built for generative artists, creative technologists, and developers building AI-native creative tools.
Full Access Unlocked
All 46 prompts · All 5 modules
"The Gray-Scott reaction-diffusion prompt is the most complete GPU implementation I've found anywhere..."
Generative Artist · 12K ETH in NFT sales
Need expert implementation?
Hire an OrchestratorConnect with a certified Prompt.Doctor Orchestrator to deploy this framework for you.
No coding required. You will use ChatGPT or Claude as your AI tool. Follow these steps in order — do not skip ahead.
Purchase & download the framework
Click the buy button on this page. After checkout, go to the and hit Download .zip. Unzip it — you'll get a .md file (the full framework) and a .pdf (easy to read reference). Keep both open.
Open your project — new or existing
This dashboard is designed to integrate into any existing project or be built as a standalone app. If you already have a site in Airo (or Cursor, Bolt, etc.), open that project. If you're starting fresh, create a new project. The Orchestrator Prompt handles both cases — it scans what's already there and adds only what's missing.
Paste the Orchestrator Prompt into your builder's chat
Open the on this page. Copy the Orchestrator Prompt and paste it into your AI builder's chat. It will scaffold the full admin system — secure login, email marketing module, booking engine, and CMS — on top of your existing codebase. This takes 2–5 minutes.
Add your API keys as secrets
Critical — Novice UsersIn your builder, go to Settings → Secrets and add the keys your app needs. For this framework: STRIPE_SECRET_KEY (for booking payments — get it from your Stripe dashboard), ANTHROPIC_API_KEY (for AI-assisted content — get it from console.anthropic.com), and DATABASE_URL (your MySQL connection string). No key is needed for the admin login, CMS, or email modules — those run on your existing infrastructure.
Don't have a MySQL server?
You can purchase a shared hosting plan with cPanel and MySQL at host.esgwon.dev. Once your account is set up, follow the step-by-step guide to create your database and connect it to your AI website builder.
How to set up cPanel MySQL & connect to your AI website →Need help with Stripe?
Get your STRIPE_SECRET_KEY and STRIPE_PUBLISHABLE_KEY from your Stripe dashboard. The guide covers test keys, webhook setup, and going live.
Need help with Anthropic?
Get your ANTHROPIC_API_KEY from console.anthropic.com. The guide covers model selection, cost management, and troubleshooting.
Prompting Airo after setup — always name the file
When asking Airo to add tables, columns, or features to the admin dashboard, always include src/server/lib/admin-db.ts in your prompt. Without it, Airo may target the wrong database. Example: "Add a bookings table in the admin database (src/server/lib/admin-db.ts) — do not touch any other database connection in this project."
Run the framework prompts inside your live app
Your app is now running in the builder's preview panel. Open the on this page, copy each prompt one at a time, and paste it into your builder's chat. Replace every [BRACKET] with your real data before sending. Work through the stages in order — each stage output feeds the next.
Test end-to-end, then publish or hand off to your client
Walk through the admin as a real user: log in, create a booking, send a test email campaign, update a CMS image, and run the Safe-to-Publish gate. Once everything passes, click Publish in your builder. Because this is a white-label dashboard, your client accesses it at /admin on their own domain — no Prompt.Doctor branding, no third-party login required.
5 modules · 46 prompts · 5 workflow stages
Procedural Geometry
L-system tree and coral generator, Catmull-Clark subdivision surface, parametric torus knot variants, Voronoi-based mesh fragmentation, and noise-displaced sphere
10 promptsGLSL Generative Shaders
Gray-Scott reaction-diffusion on GPU (ping-pong framebuffers), Voronoi growth animation, cellular automata (Game of Life on GPU), and Truchet tile patterns
10 promptsAI Parameter Mapping
LLM prompt → JSON seed generation, seed-to-parameter mapping functions, deterministic PRNG from seed, and parameter space documentation for LLM context
9 promptsAnimation & Evolution
Time-evolving generative systems, smooth parameter interpolation between states, generative music visualization, and chaos/order transition animations
9 promptsExport & Composition
High-res canvas capture (4K render target), deterministic seed system for reproducibility, NFT metadata JSON generation, and multi-layer composition system
8 promptsWrite a WebGL 2.0 (or React Three Fiber with custom ShaderMaterial) Gray-Scott reaction-diffusion simulation running entirely on the GPU using ping-pong framebuffers. Requirements: (1) Two render targets (WebGLRenderTarget, 512x512, RGFormat — R channel = U concentration, G channel = V concentration). (2) Simulation shader (fragment): read current UV concentrations from the input texture. Apply Gray-Scott equations: du/dt = Du * laplacian(U) - U*V^2 + F*(1-U), dv/dt = Dv * laplacian(V) + U*V^2 - (F+K)*V. Laplacian: 5-point stencil with texelFetch (WebGL2) or manual offset sampling. Uniforms: u_feed (F), u_kill (K), u_Du, u_Dv, u_dt, u_texelSize. (3) Display shader: map V concentration to a color gradient — 0.0 = deep navy (#0A0F1A), 0.3 = electric cyan (#00E5FF), 0.6 = white, 1.0 = gold (#FFD700). (4) Preset parameter sets (provide as constants): "coral" (F:0.0545, K:0.062), "mitosis" (F:0.0367, K:0.0649), "maze" (F:0.029, K:0.057), "spots" (F:0.035, K:0.065). (5) Seed: initialize with a small circle of V=1 at center, U=1 everywhere else. (6) Run 8 simulation steps per render frame for faster convergence. (7) Expose as a React component with Leva controls for F, K, Du, Dv, and preset selector. Full TypeScript.
Write a system that takes a text prompt from a user, sends it to an LLM API, and receives a structured JSON seed that drives a generative 3D art system. Requirements: (1) System prompt for the LLM: "You are a generative art parameter system. Given a text description, output ONLY a valid JSON object with these exact fields: { seed: number (0-999999), geometry: { type: 'lsystem'|'subdivision'|'parametric', complexity: 1-10, symmetry: 1-8, scale: 0.5-3.0 }, shader: { type: 'reaction_diffusion'|'voronoi'|'cellular', feedRate: 0.01-0.08, killRate: 0.04-0.07, speed: 0.5-3.0 }, palette: { primary: hex, secondary: hex, accent: hex, background: hex }, animation: { speed: 0.1-2.0, chaos: 0.0-1.0, evolution: 'grow'|'pulse'|'drift' } }. Map the emotional and visual qualities of the description to these parameters intuitively." (2) TypeScript: GenerativeSeed interface matching the JSON schema. (3) seedToScene(seed: GenerativeSeed): deterministic function that uses a seeded PRNG (provide a mulberry32 implementation) to generate all random values in the scene from the seed number — ensuring the same seed always produces the same artwork. (4) Leva GUI: after receiving the seed, display all parameters in a Leva panel allowing manual override. (5) API call: POST to /api/generate-seed with { prompt: string }, return GenerativeSeed. Provide the Express route handler. Full TypeScript end-to-end.
system
19 prompts
templates
10 prompts
workflow
9 prompts
prompts
8 prompts
"The Gray-Scott reaction-diffusion prompt is the most complete GPU implementation I've found anywhere — tutorials, papers, or AI. The 8-steps-per-frame optimization, the texelFetch laplacian, the preset parameter sets — it's production-ready on the first generation."
Generative Artist
12K ETH in NFT sales
"The LLM seed-to-parameter mapping system is the architecture our entire platform is built on. The idea of using the LLM as a parameter space explorer — not a code generator — and the deterministic PRNG that makes every seed reproducible, is genuinely novel."
Creative Technologist
AI art platform, 40K users
All 46 prompts across 5 modules are unlocked for your account.
Lifetime access