Visions of Chaos
Local AI software combines image, video, audio and 3D generation with fractal simulations. Models run on your hardware without online APIs or usage telemetry.
Visions of Chaos combines generative AI tools with fractals and complex-system simulations in one application. It's for digital artists, educators and people who want to explore machine learning or mathematical patterns without working through the equations themselves. Its AI models run privately on your own hardware, without paid online APIs or backend usage logging and telemetry.
Image tools cover generation, editing, inpainting and upscaling, with support for Stable Diffusion, Flux, ComfyUI and InvokeAI. Video capabilities include generation, animation and frame interpolation. For 3D work, it includes depth mapping and mesh generation tools such as Hunyuan3D, TRELLIS and TripoSR.
Audio tools span music generation, text-to-speech, voice conversion and speech recognition. Named options include MusicGen, Bark, Chatterbox and Whisper. Text and multimodal tools include llama.cpp, Text Generation Web UI and Qwen2.5-VL. Model training tools such as Dreambooth, OneTrainer and LLaMA-Factory are also part of the application.
The simulation side gives it a different scope from a dedicated AI image generator. You can explore cellular automata, fluid behavior, reaction diffusion and particle systems, or generate Mandelbrot and Julia fractals. Ready-made sample files provide starting points, while customization controls let experienced users shape the output. A GLSL formula editor and compiler supports custom shaders and fractal formulas.
The Windows app is freeware, including commercial app use. ML modes require an NVIDIA GPU and a substantial Python/CUDA and build-tool installation. Downloaded models have separate terms, which can restrict commercial use.
