发表机构
School of Interactive Arts and Technology, Surrey, Canada（交互艺术与技术学院，英国苏城）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究探讨创意实践中可解释人工智能，提出以实验和干预为中心的方法，通过集成模型调整和交互界面到工作流程，经对Stable Diffusion 1.5分析，助艺术家理解模型组件对生成图像的影响，让大型模型成为创意材料。
AI 中文摘要
创意实践中的可解释人工智能（XAI），与其说是以技术为中心的解释，不如说是让艺术家能够在创作过程中检查、修改和调试模型。然而，大规模文本到图像的扩散系统通常被视为不透明的端到端工具，限制了这种实质性的参与。我们认为，当大型模型的内部结构变得可见且可操作时，它们可以作为创意材料。为了支持这一点，我们提出了一种以实验和干预为中心的实践性可解释性方法。我们通过将模型调整和交互式（检查）界面集成到ComfyUI基于节点 的工作流程中，包括交互式层选择和干预控制，来实例化这种方法。通过对Stable Diffusion 1.5中调整干预的定性和定量分析，我们展示了如何操纵扩散管道的特定组件产生相对一致的视觉效果家族，使艺术家能够建立关于模型不同部分如何塑造生成图像的实用层面直觉。
英文摘要
Explainable AI (XAI) in creative practice can be less about technocentric explanation and more about enabling artists to inspect modify and debug models as part of making Yet largescale texttoimage diffusion systems are typically presented as opaque endtoend tools limiting this kind of material engagement We argue that even large models can function as creative materials when their internal structure is made visible and manipulable To support this we propose a handson approach to explainability centred on experimentation and intervention We instantiate this approach with a model bending and an interactive (inspection) interface integrated into ComfyUIs nodebased workflow including interactive layer selection and intervention controls Through qualitative and quantitative analysis of bending interventions in Stable Diffusion 15 we show how manipulating specific components of a diffusion pipeline produces relatively consistent families of visual effects allowing artists to build practical layerlevel intuition about how different parts of the model shape generated images
CommentsUnder review for "Explainable AI for the Arts" (N. Bryan-Kinns, Ed.), Springer
