AI生成艺术已突破工具范畴，开启人机共创新阶段。
Goetterfunke: Creativity in Machinae Sapiens. About the Qualitative Shift in Generative AI with a Focus on Text-To-Image
- 聚焦文本到图像系统，解析生成式AI的创意跃迁机制
- 人类与AI协作产生高质量艺术作品，展现机器自主创作潜力
- 适合关注艺术生成、人机协同与人工智能伦理的读者
2022年标志着技术乃至人类历史的分水岭，当时强大的生成式AI问世，能够逼真地完成创造性任务。借助这些系统，任何人皆可创作出以往被视为杰出艺术品的作品。在人机协作中，计算机似乎已超越工具角色。许多初次接触当前生成式AI的人将其视为“创造力机器”，而另一些人则认为“机器创造力”本身是自相矛盾的。本文探讨在现有机器学习范式下，计算机是否具备创造力，概述关键技术概念与推动这一质变的创新，重点聚焦文本到图像系统。讨论了人工智能创造力的本质及其对艺术的意义，指出AI可能成为具备独立创作元素的艺术创作合作者。
原文摘要 · Abstract (English)
The year 2022 marks a watershed in technology, and arguably in human history, with the release of powerful generative AIs capable of convincingly performing creative tasks. With the help of these systems, anyone can create something that would previously have been considered a remarkable work of art. In human-AI collaboration, the computer seems to have become more than a tool. Many who have made their first contact with current generative AIs see them as "creativity machines" while for others the term "machine creativity" remains an oxymoron. This article is about (the possibility of) creativity in computers within the current Machine Learning paradigm. It outlines some of the key concepts behind the technologies and the innovations that have contributed to this qualitative shift, with a focus on text-to-image systems. The nature of Artificial Creativity as such is discussed, as well as what this might mean for art. AI may become a responsible collaborator with elements of independent machine authorship in the artistic process.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。