Protosampling: Enabling Free-Form Convergence of Sampling and Prototyping through Canvas-Driven Visual AI Generation

TL;DR

This paper introduces 'protosampling', a new creative process combining sampling and prototyping enabled by generative AI, exemplified through Atelier, a visual system that fosters exploration and convergence in creative workflows.

Contribution

It defines and operationalizes 'protosampling' using a novel system, Atelier, which integrates generative models into a unified visual workspace for creative exploration.

Findings

Atelier enables seamless blending of references and generated assets.

The system supports interactive visualizations and smart search for creative exploration.

Protosampling shifts focus to the process of creative convergence rather than just outcomes.

Abstract

As an emergent process, creativity relies on explorations via sampling and prototyping for problem construction. These activities compile knowledge, provide a context enveloping the solution, and answer questions. With Generative AI, practitioners can go beyond sampling existing media towards instantly generating and remixing new ones. We refer to this convergence as 'protosampling'. Using existing literature we ground a definition for protosampling and operationalize it through Atelier, a canvas-like system that leverages a variety of generative image and video models for visual creation. Atelier: (1) blends the spaces for thinking and creation, where both references and generated assets co-exist in one space, (2) provides various encapsulated technical workflows that focus on the activity at hand, and (3) enables navigating emergence through interactive visualizations, smart search, and collections. Protosampling as a lens reframes creative work to emphasize the process itself and how seemingly disjointed thoughts can tightly interweave into a final solution.