Pixelbot 3000 turns basic AI suggestions into Lego mosaic masterpieces

Share

A dedicated YouTuber, yes designed and built a Lego printer that can automate the process of assembling intricate mosaics of blocks, similar to Lego art sets such as da Vinci Mona Lisa or Hokusai The Great Wave. But while the creation draws inspiration from another Lego printer called Bricassoimproves the process using artificial intelligence.

While technically impressive when it debuted eight years ago, Jason Allemann Bricasso required a complicated process in which mosaic designs had to be created by hand, printed on paper, and then scanned with the machine’s camera. YouTube channel Creative brainstorming used custom code and artificial intelligence, so generating a Lego mosaic requires one basic input.

WITH Pixelbot 3000, users simply need to enter what graphics they want to create on the printer. The hint is sent to OpenAI’s DALL-E 3, whose source code requests to be generated in a cartoon style to create a simplified image of 1024 x 1024 pixels.

Mosaics assembled by the printer are restricted to a much smaller grid of just 32 x 32 Lego tiles, but instead of resizing the DALL-E 3-generated image to make it smaller, the Pixelbot 3000 code splits the AI-generated image into a 32 x 32 grid and samples the color of the center pixel in each square. The result is a scaled, high-contrast image that ultimately creates a better mosaic.

Another limitation imposed by the employ of Lego as an artistic medium is that the plastic bricks are only available in about 70 different colors, and the Pixelbot 3000 only uses 15 of them. The AI-generated scaled image requires a final pass to find the closest match of each colored pixel to the 1 x 1 Lego tiles used to assemble the final mosaic.

Designing, building, and programming Pixelbot 3000 seems to require as much work as assembling one of those Lego mosaics that may be over 11,000 pieces In size. If you really want to de-stress, take 15 minutes to watch Imaginative Mindstorms take the Pixelbot 3000 from concept to functional reality.

Latest Posts

More News