IBM Patents a Way to Edit AI-Generated Content by Drawing on It
Instead of typing out a long explanation of what you want to change in an AI-generated document or image, IBM's new patent…
Generating and remaking pictures: text-to-image, video synthesis, upscaling, and the editing tricks that redraw photos after the shutter clicks.
Instead of typing out a long explanation of what you want to change in an AI-generated document or image, IBM's new patent…
When an AI generates a video, the random starting point it picks can mean the difference between a coherent clip and a…
Upscaling a single game frame is one problem. Making a hundred consecutive frames look like they belong together is a harder one.…
Google has patented a system that generates videos from plain text by passing the output through a chain of AI models, each…
Google is patenting a system where AI not only generates ad images but also figures out what those images should look like…
Most AI photo-restoration tools treat every part of an image equally. Samsung's new patent flips that assumption, training its model on the…
Samsung is patenting a system where three AI models work in sequence: one picks content, another writes a title for the picks,…
Sony is patenting a way to make low-resolution video look sharper by teaching an AI to remember where every pixel was in…
AI video upscaling looks great, but it's expensive to run on every single frame. Intel's new patent describes a system that only…
Nvidia is patenting a way to use neural networks to figure out what color a pixel should be, not just from the…
Nvidia has patented a processor-level system that uses neural networks to generate images from noise values, the same core idea behind modern…
Before an AI can generate a picture, it has to learn how to compress one. Nvidia's latest patent attacks that compression step…
One Big Tech patent every Sunday. Free.