A data-flow network-based interactive evolutionary design framework is presented which will provide a testbed for the development and exploration of a diverse range of visual artistic design spaces. The domain of real-time layered video filters is focused on as the primary example. The system supports both real-time video streams and prerecorded video. Issues of stylistic signature, GA vs. GP-based approaches, rapid tuning of fitness distributions, and desirable traits of generic evolutionary design systems are discussed.