SketchAgent: Language-Driven Sequential Sketch Generation
This addresses the problem of interactive and dynamic sketch generation for users in creative and human-computer interaction domains, though it appears incremental as it builds on existing multimodal LLMs.
The authors tackled the challenge of capturing the dynamic and abstract nature of human sketching by introducing SketchAgent, a language-driven sequential sketch generation method that enables users to create, modify, and refine sketches through conversational interactions without training, leveraging off-the-shelf multimodal LLMs.
Sketching serves as a versatile tool for externalizing ideas, enabling rapid exploration and visual communication that spans various disciplines. While artificial systems have driven substantial advances in content creation and human-computer interaction, capturing the dynamic and abstract nature of human sketching remains challenging. In this work, we introduce SketchAgent, a language-driven, sequential sketch generation method that enables users to create, modify, and refine sketches through dynamic, conversational interactions. Our approach requires no training or fine-tuning. Instead, we leverage the sequential nature and rich prior knowledge of off-the-shelf multimodal large language models (LLMs). We present an intuitive sketching language, introduced to the model through in-context examples, enabling it to "draw" using string-based actions. These are processed into vector graphics and then rendered to create a sketch on a pixel canvas, which can be accessed again for further tasks. By drawing stroke by stroke, our agent captures the evolving, dynamic qualities intrinsic to sketching. We demonstrate that SketchAgent can generate sketches from diverse prompts, engage in dialogue-driven drawing, and collaborate meaningfully with human users.