The age of AI enters a new era with image generation tools like DALL-E 2, Midjourney and Stable Diffusion. digitalfoundry puts all three through their paces - and mulls over the implications for game development.
AI-generated imagery is here. Type a simple description of what you want to see into a computer and beautiful illustrations, sketches, or photographs pop up a few seconds later. By harnessing the power of machine learning, high-end graphics hardware is now capable of creating impressive, professional-grade artwork with minimal human input. But how could this affect video games? Modern titles are extremely art-intensive, requiring countless pieces of texture and concept art.
There's another form of prompting that involves giving the software a base image to work with, along with a verbal prompt that essentially guides the software to create a new image. Right now this is only available in Stable Diffusion. Like many other AI techniques, AI image generation works by sampling a large variety of inputs - in this case, databases of images - and coming up with parameters based on that work.
But what if we generated all-new assets instead of merely trying to add detail? That's where AI image generation comes in. Take the Chrono Cross remaster, for example. The original game's artwork is pretty low resolution and the AI upscaling work does a reasonable job but ends up looking a bit messy. However, if we feed the source imagery into Stable Diffusion and add appropriate prompt material, we can generate all-new high quality artwork that maintains similar visual compositions.
Potentially, Stable Diffusion seems quite powerful for these sorts of applications, as you can easily queue up hundreds of images at once on your computer for free and cherry-pick the best results. DALL-E 2 and Midjourney also don't currently allow you to work from a specific source image, so trying to match a piece of existing art is much more challenging. Stable Diffusion also has an option to generate tileable images, which should help with creating textures.
Impressive results are achievable but it is important to stress that current AI models are hardly infallible. Actually working out a coherent aesthetic across multiple pieces of artwork can be tricky, as even an identical set of descriptive keywords produce quite different results depending on what you ask it to depict. Different subject areas in commercial artwork tend to use different techniques and this gets reflected in the AI outputs.
日本 最新ニュース, 日本 見出し
Similar News:他のニュース ソースから収集した、これに似たニュース記事を読むこともできます。
Look good, feel good, play good? The growing importance of image in footballFrom Firmino's teeth, to Ronaldo's abs and Marta's lipstick, image is everything to the modern footballer. SarahShepSport discovers the cosmetic measures players take and how they aid their commercial value - and their on-pitch performances.
続きを読む »
The ultimate UI design guideDiscover top techniques and tools for creating great UI design.
続きを読む »
Verso's New Retinol Molecule Means Good Things for Your FaceThere’s serious scientific nous behind Verso’s very good-looking bottles
続きを読む »
Unique snapshots of Manchester's streets, people and life in 1975The photos were taken by international student and featured in 'Human Images from England' exhibition
続きを読む »