Regenesis is a live experiment in recursive generation, where community-chosen visuals are regenerated infinitely to observe patterns of drift, entropy, and artificial evolution.
Regenesis is an experimental investigation into AI feedback loops, leveraging community-voted images to study the progressive distortion and emergent behavior of iterative regeneration.
1. Community members vote on candidate images to be included in the feedback loop experiment.
2. The winning image becomes the seed for a regeneration cycle.
3. Our system repeatedly regenerates the image, using each output as the input for the next iteration.
4. The resulting sequence reveals fascinating patterns of how AI systems interpret and transform visual information over time.
Token-Gated Creation: Soon, users will be able to create their own feedback loops through our token-gated system, ensuring high-quality submissions.
Advanced Analytics: We're developing tools to analyze patterns in image evolution across thousands of iterations.
Community Governance: Token holders will help guide the direction of our research and experiments.
Cross-Modal Experiments: Future plans include expanding beyond images to explore text, audio, and other media types.