Prism – An AI-Driven Generative Art System That Evolves over Time
Hey HN, I’m excited to share PRISM, an open-source system we’ve been building that fuses multiple AI models (OpenAI, Anthropic, and FAL API) with Processing to create evolving geometric art and static images. The idea came from our fascination with how AI can generate new forms but often lacks a memory or evolutionary approach. PRISM aims to solve that by “remembering” past successes and failures and then adapting its creative approach over time + useful for automating batches and variations of specific styles of techniques with prompt adjusting. *Key Features:* - Multi-model AI Generation:…
What it does
In the maker’s words, at launch
Hey HN, I’m excited to share PRISM, an open-source system we’ve been building that fuses multiple AI models (OpenAI, Anthropic, and FAL API) with Processing to create evolving geometric art and static images. The idea came from our fascination with how AI can generate new forms but often lacks a memory or evolutionary approach. PRISM aims to solve that by “remembering” past successes and failures and then adapting its creative approach over time + useful for automating batches and variations of specific styles of techniques with prompt adjusting. *Key Features:* - Multi-model AI Generation: Code and images produced by GPT-like models, Claude variants, and FAL Flux. - Evolutionary Memory: Each pattern generation is analyzed; successful techniques become more likely in future generations. - Processing Integration: Animations are rendered via Processing on Windows (with plans to expand cross-platform). - Interactive Menu System: Easy to navigate, choose models, generate single/batch patterns, or run continuous mode. - Roadmap for Growth: We plan to add a web interface, advanced pattern analysis, real-time collaboration, and more. *Tech Stack & Challenges:* - *Python* for the orchestration, hooking into each AI API (OpenAI, Anthropic, FAL). - *Processing 4.0+* for rendering animations. - *Evolutionary Approach*: We track performance metrics (visual complexity, motion quality, aesthetic evaluation) to shape future generations. - We had to tackle issues like ensuring code output from GPT/Claude is valid Processing code, managing timeouts, and orchestrating multiple model calls in parallel. *Why We Built This:* We wanted to see if AI can become a “creative collaborator” instead of just a single-shot generator. By incorporating an evolving memory and multiple model personalities, we aim for more diverse and interesting results. *How to Try It:* 1. Clone the repo: `git clone https://github.com/P-R-I-S-M-PROJECT/P.R.I.S.M.git` 2. Install requirements (`pip install -r requirements.txt`) and set your `.env` with API keys. 3. Run `python prism.py` on Windows with Processing installed (roadmap includes broader OS support soon). *Questions for HN:* - Does this “multi-model + evolutionary” approach resonate with you? How might we improve it? - Any suggestions for better pattern analysis or new AI integrations? - Feedback on user experience or installation process? GitHub Link: [https://github.com/P-R-I-S-M-PROJECT/P.R.I.S.M] Thanks for checking it out! I’ll be around to answer any questions or hear your thoughts on making this a better tool for the creative coding community.
Does the same job
all alternatives →
- ASA stream of AI-generated art2020 · art42.net · ▲277
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 26d ago · cactuscompute.com
Launched alongside, January 2025
the whole month →- IM
Hello! I'm Byran. I spent the past ~6 months engineering a laptop from scratch. It's fully open-source on GH at: https://github.com/Hello9999901/laptop
Dev tools · 2025 · byran.ee
- TITetris in a PDF▲1,289
I realized that the PDF engines of modern desktop browsers (PDFium and PDF.js) support JavaScript with enough I/O primitives to make a basic game like Tetris. It was a bit tricky to find a union of features that work in both engines, but in the end it turns out that showing/hiding annotation "fields" works well to make monochrome pixels, and keyboard input can be achieved by typing in a text input box. All in all it's quite janky but a nice reminder of how general purpose PDF scripting can be. The linked PDF is all ASCII so you can just open it in a text editor, or have a look at…
Life & fun · 2025 · th0mas.nl
Create lifelike, personalized AI avatars from text prompts
AI · 2025 · jogg.ai
