AI & RoboticsNews

Scenario plans to launch its AI art platform for 20k creators

Connect with top gaming leaders in Los Angeles at GamesBeat Summit 2023 this May 22-23. Register here.


Scenario today announced its plans to open it GenAI art engine to artists during an early access period. It’s also raised over $6 million in a new round of funding. The company boasts that its a “generator of generators” offering AI generators that users can train themselves.

Investors in this funding round include Play Ventures, Anorak Ventures, Founders, Inc, Venture Reality Fund, Sebastien Borget of Sandbox, Luc Vincent of Meta, Patrick Wyatt of One More Game, Hamilton Chu of Second Dinner and Justin Kan of Twitch. Scenario currently employs eight people, and is headquartered in San Francisco.

Scenario’s custom generators are trained with a set of images and prompts, with the intention being for artists to upload their own images and produce similar ones in the same style. The GenAI produces images imitating the style of the training images, and can be used to generate things such as buildings, character models, items and maps.

These fairy avatars were created with prompts supplied by GamesBeat’s Rachel Kaser.

Emmanuel de Maistre, Scenario’s CEO, said in a statement, “Digital artists must be empowered to train their own generators, have control over their art direction and work alongside, not against, AI. No GenAI product delivers these critical elements today – Scenario exists to deliver all of them. Generative AI will be as transformational for game development as Photoshop has been for digital photography, but it cannot get there without the same commitment to consistency and ease of use.”

Event

GamesBeat Summit 2023

Join the GamesBeat community in Los Angeles this May 22-23. You’ll hear from the brightest minds within the gaming industry to share their updates on the latest developments.



Register Here

de Maistre also showed Scenario’s custom generators to GamesBeat, showing how an artist would train their AI, both through a set of images and follow-up prompts. The AI is by no means perfect, and it requires patience to find the right set of prompts to create the kinds of images the artist wants, but the results seem to be reliable and consistent. de Maistre also told GamesBeat that all data used to train custom generators is private by default, and the company intends for artists to use only their own or royalty-free images.

GamesBeat’s creed when covering the game industry is “where passion meets business.” What does this mean? We want to tell you how the news matters to you — not just as a decision-maker at a game studio, but also as a fan of games. Whether you read our articles, listen to our podcasts, or watch our videos, GamesBeat will help you learn about the industry and enjoy engaging with it. Discover our Briefings.


Author: Rachel Kaser
Source: Venturebeat

Related posts
AI & RoboticsNews

H2O.ai improves AI agent accuracy with predictive models

AI & RoboticsNews

Microsoft’s AI agents: 4 insights that could reshape the enterprise landscape

AI & RoboticsNews

Nvidia accelerates Google quantum AI design with quantum physics simulation

DefenseNews

Marine Corps F-35C notches first overseas combat strike

Sign up for our Newsletter and
stay informed!