🎨ORIBA: Transforming Artists' Original Characters into Chatbots

Accepted by UbiComp 2023 in Poster Session

cover page
Yuqian Sun*, Xingyu Li*, Ze Gao , Jun Peng
Computer Science Research Centre, Royal College of Art, London, UK
Georgia Institute of Technology, Atlanta, United States
Hong Kong University of Science and Technology, Hong Kong SAR, China
RCT AI, Beijing, China
*Indicates Equal Contribution
Paper Code(TBA) arXiv



Artist @riniifish talking to her OC Inno

Our AI Chatbot does NOT involve any image generation!



Abstract


This research delves into the intersection of illustration art and artificial intelligence (AI), focusing on how illustrators engage with AI agents that embody their original characters (OCs). We introduce 'ORIBA', a customizable AI chatbot that enables illustrators to converse with their OCs. This approach allows artists to not only receive responses from their OCs but also to observe their inner monologues and behavior. Despite the existing tension between artists and AI, our study explores innovative collaboration methods that are inspiring to illustrators. By examining the impact of AI on the creative process and the boundaries of authorship, we aim to enhance human-AI interactions in creative fields, with potential applications extending beyond illustration to interactive storytelling and more.

See our introduction tweet here.


Artist interacting with ORIBA

Key Features

1. Transforming Artists' Original Characters into Chatbots

ORIBA is an innovative AI chatbot that transforms artists' original characters (OCs) into interactive agents. This research explores the intersection of illustration art and artificial intelligence (AI), focusing on how illustrators engage with AI agents that embody their OCs.

2. Enhancing Human-AI Interactions in Creative Fields

By examining the impact of AI on the creative process and the boundaries of authorship, we aim to enhance human-AI interactions in creative fields, with potential applications extending beyond illustration to interactive storytelling and more.

3. Experimenting with latest LLM agent framework

ORIBA leverages advancements in LLM agent research, such as AutoGPT, BabyAGI, and CAMEL, to transform artists' OCs into autonomous agents. These agents can observe, reflect, and make decisions, enhancing the believability of virtual characters and reshaping artists' storytelling and illustration approaches.

4. Exploring the Boundaries of Authorship

As AI becomes more integrated into the creative process, questions about authorship arise. ORIBA explores these questions, providing insights into how AI can be a collaborative partner in the creative process.


ORIBA Workflow

The ORIBA workflow consists of the following steps:

Observation

The Agent forms an observation based on the most recent dialogue records (5 entries), summarizing what has happened.

Reflection

The Agent reflects, associating information from its own profile.

Impression

The Agent summarizes its impression of the current speaker.

Behavior

The Agent describes its current physical or facial behavior.

Action

The Agent chooses an action. By default, we provide three actions: "Normal reply", "Relate reply (relate to memories)", and "Silence".

Reply

After generating the ORIBA trajectory, the character's final reply is produced.

This approach allows artists to not only receive responses from their OCs but also observe how they think and behave. Through in-depth and informative conversations, we aim to support and facilitate the creative process of authors.

Poster

BibTeX

@article{sun2023oriba,
  title={ORIBA: Transforming Artists' Original Characters into Chatbots},
  author={Sun, Yuqian and Li, Xingyu and Gao, Ze},
  year={2023},
  publisher={ArXiv}
}