Smart lighting company Govee has a new product that creates a quirky new product category. The Gaming Pixel Light displays still or animated pixel art set to 8-bit soundtracks. It can also show you weather updates, sports schedules and Bitcoin prices on its retro display. But it wouldn't be a CES 2025 gizmo without AI something or other stuffed inside, so you won't be surprised to learn that its companion app lets you generate AI pixel art from text prompts. As the product name suggests, the Gaming Pixel Light is marketed as a (desktop or wall-mounted) lighting companion for gamers.

Sure, Govee has some new smart lights to unveil at CES this year, but what this smart lighting manufacturer really wants to talk about is, of course, the buzzword of the show: AI. From its AI-powered gaming lights to its light-scene-creating AI chatbot, Govee clearly sees its budding AI efforts as the best way to set itself apart in the crowded smart lighting market, and the company isn't being timid about putting AI front and center. The star of the show is Govee's smart lighting-focused AI model, newly upgraded to 12 billion parameters, up from just 0.86B parameters in the previous version Trained on more than 10,000 lighting effects, Govee's model is the brains behind its text-to-image AI Lighting Bot, which allows users to create and edit smart light effects using natural-language text prompts. There's also AI Dreamview, a Govee technology that applies their newly created effects across groups of smart lights. To be clear, Govee does have some actual smart lights to show off at CES, including a new and portable table lamp that doubles as a Bluetooth speaker.

Diffusion models have shown impressive results in text-to-image synthesis. Using massive datasets of captioned images, diffusion models learn to generate raster images of highly diverse objects and scenes. However, designers frequently use vector representations of images like Scalable Vector Graphics (SVGs) for digital icons or art. Vector graphics can be scaled to any size, and are compact. We show that a text-conditioned diffusion model trained on pixel representations of images can be used to generate SVG-exportable vector graphics. We do so without access to large datasets of captioned SVGs. By optimizing a differentiable vector graphics rasterizer, our method, VectorFusion, distills abstract semantic knowledge out of a pretrained diffusion model. Inspired by recent text-to-3D work, we learn an SVG consistent with a caption using Score Distillation Sampling. To accelerate generation and improve fidelity, VectorFusion also initializes from an image sample. Experiments show greater quality than prior work, and demonstrate a range of styles including pixel art and sketches. See our project webpage at https://ajayj.com/vectorfusion .

Machine learning has had a great deal of success in image processing. However, the focus of this work has largely been on realistic images, ignoring more niche art styles such as pixel art. Additionally, many traditional machine learning models that focus on groups of pixels do not work well with pixel art, where individual pixels are important. We propose the Pixel VQ-VAE, a specialized VQ-VAE model that learns representations of pixel art. We show that it outperforms other models in both the quality of embeddings as well as performance on downstream tasks.

Playing Chucklefish's Eastward is like coming home to a place I've never been before. After its 2018 reveal, I was immediately drawn to the game's Zelda-like adventure elements, unusually colorful post-apocalyptic narrative, and motley crew of characters. But most of all, I was wowed by its gorgeous, highly detailed environments constructed entirely of pixel art. "What Eastward does best is create a world that feels like the games we played growing up," my brother said after the game's September 2021 release. It joins Extremely OK Games' puzzle-platformer Celeste and Eric Barone's mega-hit farming simulator Stardew Valley (also published by Chucklefish) in a rapidly growing club of video games tapping into nostalgia with high-end pixel art graphics and a retro aesthetic.

A year ago, Marcus Dewdney, an artist in Toronto, started a project inspired by Pokémon, the beloved series of monster-collecting video games that launched on Game Boy in the United States in 1998. He pulled up images from the 2001 games Pokémon Gold and Silver and, using the image editor paint.net, Scant grids of symbolic leaves from the original game became swirls of gnarled trees; straight lines meant to suggest cliffs became craggy, precipitous rock faces. This past March, Dewdney and several other artists completed the entire map of Gold and Silver--which can be explored screen by screen on a dedicated Web site. Now the group is working on overhauling the original Pokémon games, Red and Blue. Viewers of Dewdney's images often comment, "This is how I saw it in my head as a kid," he told me.

Listen closely and the ambient soundtrack sounds like a heartbeat rising from within the earth. In Hyper Light Drifter, available now for PC and later this year for consoles, the post-apocalypse is alive--and it's fighting. The story it tells is minimal and wordless. A short opening cutscene reveals everything the game thinks you need to know: a vision of an arcane futuristic utopia, destroyed in a burst of impossibly bright light. In the aftermath, you play as a cloak- and goggle-wearing drifter.