Has image generation AI really gotten so advanced now that it can make images that also look like other images? Last I saw it could barely make someone with 5 human-looking fingers 🤔
Yep, especially using something called “ControlNet”, you can give it a base image, then tell the AI what to generate. It’ll use the outline (or other properties) of the image to “guide” the image it generates, resulting in images like this one.
Regarding the comment about fingers, take a closer look at the architecture and especially the text/images on the signs. AI still has a ways to go, though it’s getting better by the day.
Yeah! I recommend Two Minute Papers, a YouTube channel that explores the newest advances in computer research, often on AI but including other procedural methods. It’s run by a Dr Zslonai-Fehér from Hungary with a PhD in light transport. https://youtube.com/@twominutepapers
Has image generation AI really gotten so advanced now that it can make images that also look like other images? Last I saw it could barely make someone with 5 human-looking fingers 🤔
Yep, especially using something called “ControlNet”, you can give it a base image, then tell the AI what to generate. It’ll use the outline (or other properties) of the image to “guide” the image it generates, resulting in images like this one.
Regarding the comment about fingers, take a closer look at the architecture and especially the text/images on the signs. AI still has a ways to go, though it’s getting better by the day.
Yeah! I recommend Two Minute Papers, a YouTube channel that explores the newest advances in computer research, often on AI but including other procedural methods. It’s run by a Dr Zslonai-Fehér from Hungary with a PhD in light transport.
https://youtube.com/@twominutepapers
Yeah I’ve watched it before once or twice… Great channel :)