Larian Studios Details Its Implementation of Generative AI for New Divinity Game
The team behind popular role-playing games like Baldur's Gate 3 and Divinity: Original Sin has recently teased its upcoming project, sparking significant anticipation within the player base. However, recent remarks from the company's co-founder have brought a new dimension to the conversation, touching on the developer's philosophy toward AI tools.
A Tool for Ideation, Not Replacement
In a recent clarification, Swen Vincke explained that the company is employing machine learning for specific preliminary functions. These involve developing PowerPoint slides, creating early-stage artistic references, and creating temporary text.
Crucially, Vincke emphasized that the end assets in the game will be crafted entirely by real creatives. "Our team is creating every line manually," he stated.
We are actively expanding our pool of storytellers and are currently forming writing teams.
As concept art is being explicitly referenced ā we currently have twenty-three visual developers and have roles to fill for further talent.
Each initiative we do is supplementary and focused on enabling creatives to spend more time on the creative process.
Every ML tool implemented properly is a boost to a developer's routine, not a substitute for their craft.
Addressing Concerns and Clarifying the Vision
The revelation of AI usage at first sparked unease among some the player base. In reply, Vincke provided additional elaboration on public forums.
"We use AI tools to gather inspiration, similar to we use the internet and reference books," he wrote. "During the very early planning process we use it as a rough outline for layout which we then replace with authentic illustrations."
He added, "Our studio recruits artists for their unique talent, not for their willingness to follow what a AI generates."
Key Areas of AI Integration
Vincke had in the past outlined the team's practical strategy to machine learning, defining its use into three main pillars:
- Handling Monotonous Jobs: This encompasses motion capture cleaning, dialogue cleanup, and pipeline-specific tasks like adapting animations for different models.
- Fast-Tracked Experimentation: Using tools to speedily create rough models of mechanics to validate concepts ahead of full development.
- Long-Term Aspirations: Investigating how AI could eventually enhance new forms of player agency, especially in simulating unforeseen permutations in a detailed game universe.
He specifically stated that central narrative domains ā like music composition ā are are in no way departments where the team is reducing human talent. Conversely, Larian is recruiting more in these precise roles.
"Larian is not releasing a game with any AI components, nor looking at trimming down teams to replace them with artificial intelligence," Vincke concluded.
