A Comprehensive Survey of AI-Generated Content (AIGC): A History of Generative AI from GAN to ChatGPT

Abstract

Recently, ChatGPT, along with DALL-E-2 [1] and Codex [2],has been gaining significant attention from society. As a result, many individuals have become interested in related resources and are seeking to uncover the background and secrets behind its impressive performance. In fact, ChatGPT and other Generative AI (GAI) techniques belong to the category of Artificial Intelligence Generated Content (AIGC), which involves the creation of digital content, such as images, music, and natural language, through AI models. The goal of AIGC is to make the content creation process more efficient and accessible, allowing for the production of high-quality content at a faster pace. AIGC is achieved by extracting and understanding intent information from instructions provided by human, and generating the content according to its knowledge and the intent information. In recent years, large-scale models have become increasingly important in AIGC as they provide better intent extraction and thus, improved generation results. With the growth of data and the size of the models, the distribution that the model can learn becomes more comprehensive and closer to reality, leading to more realistic and high-quality content generation. This survey provides a comprehensive review on the history of generative models, and basic components, recent advances in AIGC from unimodal interaction and multimodal interaction. From the perspective of unimodality, we introduce the generation tasks and relative models of text and image. From the perspective of multimodality, we introduce the cross-application between the modalities mentioned above. Finally, we discuss the existing open problems and future challenges in AIGC.

A special delivery by a fork: Where does artificial intelligence come from?

“…They are only able to categorize, sort, or otherwise make sense of existing information. Generative AI, as its name suggests, generates new data in response to prompts (Cao et al, 2023;Stokel-Walker & Van Noorden, 2023). Generative AI in the form of chatbots, image generators, and narrative generators are systems that are informed by extant data but designed to simulate creativity and produce novel work (Cao et al, 2023;Stokel-Walker & Van Noorden, 2023).…”

Bringing Stories to Life in 1001 Nights: A Co-creative Text Adventure Game Using a Story Generation Model

“…Furthermore, the progression of Generative AI (GenAI) (Cao et al 2023) unfolded new potentials for gameplay. GenAI depicts AI systems and models that utilize existing media to create plausible, novel media artefacts (Solaiman 2023) (Muller et al 2022).…”

Big Data and AI-driven Product Design: A Survey

“…Design methods have shifted from experiential and fuzzy design to intelligent design, computer-aided design, and multi-domain joint design [3][4][5][6]. Despite these progresses, the fierce market competition calls for next-generation product innovation and design methodologies based on the significant progress of big data, deep learning, and other AI algorithms, which have brought transformative revolution in the understanding, pattern recognition, and generative design and synthesis of text, image, video, audio, and etc [7,8].…”