If you’ve ever helplessly looked at a pile of random Lego bricks and thought “what on Earth do I make from this,” your problem has been solved. Brickit has made a really cool AI-powered app that helps you make something out of that messy pile of Legos. All you need to do is point the camera at the bricks. The app will scan them and give you suggestions of what you can make.
This AI-powered app turns your doodles into realistic “photos”
by 3 Comments
Facebook only needs one photo with the one word to copy your handwriting
by 2 Comments
Facebook has introduced a new research project that’s impressive and scary at the same time. TextStyleBrush uses AI to recreate your handwriting based on a photo of it, as hinted in its very name. And all it needs is a single word and a single photo of it.
NVIDIA launches RTX 3050 mobile GPUs for low priced laptops for creatives
by Leave a Comment
NVIDIA has today announced their new hotly-anticipated RTX 3050 and RTX 3050 Ti mobile GPUs for RTX Studio laptops. Designed for both gamers and creatives, the new GPU comes with a host of new laptops coming from the usual suspects like Dell, HP, Lenovo, etc.
The RTX 3050 takes advantage of many of the new GPU-accelerated AI features out there like Smart Portrait and Super Resolution in Photoshop, Scene Edit Detection in Premiere Pro and the Magic Mask feature in DaVinci Resolve 17, offering some significant performance gains over the previous generation NVIDIA RTX and GTX-based laptops.
Automating scanning film with the help of Lego, a Raspberry Pi and a little machine learning
by Leave a Comment
There are a lot of options out there for scanning film these days, but there’s just something about building a device yourself. This one from Benjamin Bezine does so using Lego and a Raspberry Pi. What makes this solution a little special, though, is that it uses machine learning and vision AI in order to determine the edges of frames, so you don’t need to sit and operate it manually or worry about the number of turns changing as roll thickens and thins out or counting sprockets.
It’s called RoboScan, and Benjamin’s been working on it for a while now (it’s his “lockdown project”) but he’s not finished yet! It’s an open-source project and he’s been uploading the code to GitHub. Only 80 images were used to “train” the Raspberry Pi so that it knows what to look for, but it seems that it’s very effective with just that limited set.
NVIDIA’s latest RTX Studio drivers boost new AI features from Adobe and Blackmagic
by 3 Comments
A couple of years ago, graphics card manufacturer NVIDIA decided that it was time to stop focusing just on gamers and launched their “Creator Ready” drivers. Those have since evolved into what is now called their “Studio” drivers, but they’re essentially the same thing; versions of their drivers that are geared more towards content creation rather than gaming.
They’ve seen a lot of changes over the last couple of years, especially since the launch of their first series RTX cards, and now their new March 2021 version of the Studio drivers focus heavily on the latest AI-powered tools from Adobe, including the new Super Resolution feature, as well as the newest neural engine in Blackmagic’s DaVinci Resolve 17.
The Latest Luminar AI update brings improved sky replacement, Templates, and more
by 1 Comment
Luminar AI has just launched the latest update to its AI-powered editing software. After the first major update in January, more news and improvements are now coming to the app. So, let’s dive in and see what you get if you update to the latest version.[Read More…]
AI-powered Super Resolution upscaling is now available in Adobe Camera Raw
by 2 Comments
Adobe Camera Raw now includes a new feature that will be coming soon to both Lightroom and Lightroom Classic. It’s called Super Resolution and it’s essentially a machine learning AI-powered method of upscaling that offers massive image upscaling benefits at the push of a button. Well, you have to push it a couple of times and check a box in a dialogue, but then it’s at the push of a button.
Julieanne Kost, Principal Evangelist at Adobe posted a video about the new feature to YouTube saying that the model for the new feature was trained on millions of photos, and uses that data to “intelligently boost the resolution of an image while maintaining clean edges and preserving important details”.
This website lets you merge photos with video and audio to make them talk
by Leave a Comment
After Deep Nostalgia, here’s another tool that lets you animate your still images. Tokkingheads lets you choose a photo or avatar, merge it with a video to copy the moves from it, and even add audio to your creations. It’s a bit less impressive than Deep Nostalgia, but more fun and interactive… and I got totally hooked to playing with it!
AI “Deep Nostalgia” images have deep limitations
by 5 Comments
News outlets and social media accounts have been overrun with old photos that have been animated with MyHeritage’s “Deep Nostalgia” feature, an AI-based deep learning algorithm licensed from Israeli-based D-ID.
- 1
- 2
- 3
- …
- 14
- Next Page »
FIND THIS INTERESTING? SHARE IT WITH YOUR FRIENDS!