CHIMERA PAINTER GENERATOR
CHIMERA PAINTER FULL
CHIMERA PAINTER SOFTWARE

Examples of this can include eyes, fingers, or even distinguishing between overlapping body parts with similar textures (see the affectionately named BoggleDog below). Learning to Generate Creatures with StructureДЄn issue with using GANs for generating creatures was the potential for loss of anatomical and spatial coherence when rendering subtle or low-contrast parts of images, despite these being of high perceptual importance to humans. More info about the game itself is detailed in this Stadia Research presentation. Generated card art integrated into the card game prototype showing basic creatures ( bottom row) and chimeras from multiple creatures, including an Antlion-Porcupine, Axolotl-Whale, and a Crab-Antion-Moth ( top row). Below we show some sample assets generated using the model, including single-species creatures, as well as the more complex multi-species chimeras. The best performing model was then incorporated into Chimera Painter. After model training, the model was tasked with generating multi-species chimeras, based on outlines provided by artists. The creature outlines characterized the shape and size of each creature, and provided a segmentation map that identified individual body parts.

CHIMERA PAINTER FULL

To train the GANs, we created a dataset of full color images with single-species creature outlines adapted from 3D creature models. Interestingly, our approach was a strict departure from other GAN efforts, which typically focus on photorealism.

CHIMERA PAINTER GENERATOR

We used a variant called a conditional GAN, where the generator takes a separate input to guide the image generation process. GANs pair two convolutional neural networks against each other: a generator network to create new images and a discriminator network to determine if these images are samples from the training dataset (in this case, artist-created images) or not. Since our goal was to create high-quality creature card images guided by artist input, we experimented with generative adversarial networks (GANs), informed by artist feedback, to create creature images that would be appropriate for our fantasy card game prototype. This provided a creative environment for demonstrating an image-generating model, as the number of possible chimeras necessitated a method for quickly designing large volumes of artistic assets that could be combined naturally, while still retaining identifiable visual characteristics of the original creatures. In this game, a player would begin with cards of real-world animals (e.g., an axolotl or a whale) and could make them more powerful by combining them (making the dreaded Axolotl-Whale chimera). In developing an ML model to produce video-game ready creature images, we created a digital card game prototype around the concept of combining creatures into new hybrids that can then battle each other. In this post, we describe some of the challenges in creating the ML model behind Chimera Painter and demonstrate how one might use the tool for the creation of video game-ready assets. In this example, an artist (Lee Dotson) customizes one of the creature designs that comes pre-loaded in the Chimera Painter demo. Using an image imported to Chimera Painter or generated with the tools provided, an artist can iteratively construct or modify a creature outline and use the ML model to generate realistic looking surface textures. Below is an example using the demo with one of the preset creature outlines. Employed as a demo application, Chimera Painter adds features and textures to a creature outline segmented with body part labels, such as вЂњwingsвЂќ or вЂњclawsвЂќ, when the user clicks the вЂњtransformвЂќ button. Today, we present Chimera Painter, a trained machine learning (ML) model that automatically creates a fully fleshed out rendering from a user-supplied creature outline. What if artists had a paintbrush that acted less like a tool and more like an assistant? A machine learning model acting as such a paintbrush could reduce the amount of time necessary to create high-quality art without sacrificing artistic choices, perhaps even enhancing creativity.

CHIMERA PAINTER SOFTWARE

Posted by Andeep Singh Toor, Stadia Software Engineer and Fred Bertsch, Software Engineer, Google Research, Brain TeamД¬reating art for digital video games takes a high degree of artistic creativity and technical knowledge, while also requiring game artists to quickly iterate on ideas and produce a high volume of assets, often in the face of tight deadlines.

Chimera painter