Show HN: Prism – An AI-Driven Generative Art System That Evolves over Time https://ift.tt/q6VEe7i

Show HN: 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: 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://ift.tt/ZCXQH6l ` 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://ift.tt/xrq4Hfp ] 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. https://ift.tt/xrq4Hfp January 24, 2025 at 04:20AM