Downloads provided by UsageCounts
We present Genny, a live coding interface for interacting with generative models. By implementing a streamlined generative model API within a Web-based live coding environment, we explore possibilities for how generative models can support live coding. We describe the implementation of our interface components and the backend system for working with generative models, show several design patterns with template code, and describe use of a practical generation method for live coding performance. The system currently enables the generation of two-bar rhythm patterns using lightweight models that support near-instantaneous inference, which are able to suggest and display alternative rhythm patterns based on live coders’ own inputs. Finally, we discuss reflections on this implementation approach, its current limitations, and further possibilities.
live coding, machine learning, generative models, human-computer interaction
live coding, machine learning, generative models, human-computer interaction
| selected citations These citations are derived from selected sources. This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | 0 | |
| popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network. | Average | |
| influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | Average | |
| impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network. | Average |
| views | 100 | |
| downloads | 89 |

Views provided by UsageCounts
Downloads provided by UsageCounts