DAM 3D has there been a technology so revolutionary for gaming. Spend any time talking to the game's creators, and the sense of excitement and wonder is palpable. So where will this technology go? How will it change the game? But first, let’s review what is Generative AI?

What is generative artificial intelligence

Generative AI is a type of machine learning in which computers can generate original new content based on user prompts. Today, text and images are the most mature applications of this technology, but work is being done in almost every creative field, from animation to sound effects to music and even creating virtual characters with fully fleshed-out personalities.

Of course, the use of artificial intelligence in games is nothing new. Even early games, such as Atari's Pong, had computer-controlled opponents to challenge the player. However, these virtual enemies did not run artificial intelligence as we know them today. They are just scripts written by game designers. They simulated an AI opponent, but they couldn't learn, they were only as good as the programmers who built them.

The difference now is the computing power available, thanks to faster microprocessors and cloud computing. With this capability, large neural networks can be built to recognize patterns and representations in highly complex domains.

2D images

Generating 2D images based on text prompts is already one of the most widely used areas of generative artificial intelligence. Tools such as Midjourney, Stable Diffusion, and Dall-E 2 can generate high-quality 2D images from text and have found their way into game production at multiple stages of the game lifecycle

Generative AI tools are good at “ideasing,” or helping non-artists (such as game designers) quickly explore concepts and ideas to generate concept drawings, a key part of the production process. For example, one studio (who remains anonymous) is using several of these tools to radically speed up their concept art process, taking just a day to create an image that previously took up to 3 weeks.

First, their game designers used Midjourney to explore different ideas and generate images they found inspiring.
These were handed over to professional concept artists, who assembled them together and painted over the results to create a single coherent image – which was then fed into Stable Diffusion to create a series of variations.
They discuss the changes, select one, draw some edits by hand—and then repeat the process until they're satisfied with the results.
At that stage, this image is passed back to Stable Diffusion one last time to "upgrade" it to create the final artwork.

2D production art

Some studios are already experimenting with using the same tools to create in-game artwork. For example, here's a great tutorial from Albert Bozesan on how to use Stable Diffusion to create 2D assets for your game.

3D artwork

3D assets are the cornerstone of all modern games, as well as the upcoming metaverse. A virtual world or game level is essentially just a collection of 3D assets that are placed and modified to populate the environment. However, creating 3D assets is more complex than creating 2D images and involves multiple steps, including creating 3D models and adding textures and effects. For animated characters, it also involves creating an internal "skeleton" and then creating the animation on top of that skeleton.We see several different startups working on every stage of this 3D asset creation process, including model creation, character animation, and level building. However, this is not a solved problem yet – no solution is ready to be fully integrated into production.

3D texture

The realism of a 3D model depends on the textures or materials applied to the mesh. Deciding which mossy, weathered stone texture to apply to your medieval castle model can completely change the look and feel of your scene. Textures contain metadata about how light reacts to the material (i.e. roughness, glossiness, etc.). Allowing artists to easily generate textures based on text or image cues is extremely valuable for increasing the speed of iteration during the creative process.

A few people have specifically tried to build chatbots for entertainment purposes, such as Replika and Anima, which try to build virtual friends. As explored in the movie Her, the concept of dating a virtual girlfriend might be closer than you think. We are now seeing the next iteration of these chatbot platforms, such as Charisma.ai, Convai.com, or Inworld.ai, aiming to provide fully rendered 3D characters with motivation, emotion, and agency, as well as providing tools for creators to provide these Character goals. This is important if they are to be integrated into the game or have a narrative place in advancing the plot, rather than being purely window dressing.

All-in-one platform

Runwayml.com is one of the most successful generative AI tools as it brings together an extensive suite of creator tools in one package. There is currently no such video game platform, and we believe this is an overlooked opportunity. We'd love to invest in solutions that:

A complete set of AI-generated tools covering the entire production process. (code, asset generation, textures, audio, descriptions, etc.)
Tightly integrated with popular game engines such as Unreal and Unity.
Designed to fit into typical game production workflows.

This is an incredible time for game creators! Thanks in part to the tools described in this blog post, generating the content you need to build your game has never been easier—even if your game is as big as the entire planet! It's even possible to one day imagine a completely personalized game, built entirely for players based on their needs.

What are the application markets for artificial intelligence revolution in games Using Blueberry?