#diffusion models
7 stories taggeddiffusion models.
Why AI-Generated Food Looks So Wrong (and So Revolting)
Restaurants and cafés are using AI image tools to promote their menus. The results, noodly, holey, deeply unsettling, are not winning any appetites. Here is the science behind why.
Why AI restaurant menus look weirdly perfect and slightly wrong
Shrimp curling into themselves, impossibly glossy buns, ice cream scoops so round they look engineered. There is a real technical reason AI food illustrations give you the creeps.
How do AI image generators actually work? A plain-English guide
From typed words to finished artwork in seconds: here is what is actually happening inside the machine.
Apple Researchers Found a Smarter Way to Make AI Video Generation Much Faster
A new technique from Apple ML Research cuts the time it takes AI to turn text prompts into video, by teaching the model to skip calculations it doesn't actually need.
NVIDIA and Hugging Face team up to make training giant image and video AI models far easier
A new open-source tool lets developers fine-tune some of the largest image and video generators available, on hardware ranging from a single machine to hundreds of chips, with no complicated file conversions.
One Layer Does the Job: Apple Research Finds a Smarter Way to Teach AI to Generate Images
Apple ML Research shows that adapting a single layer of a pre-trained visual encoder is enough to improve image generation quality, sharper results without retraining the whole model.
South Korean Researchers Used AI to Design DNA That Folds Itself into Tiny Shapes
A new AI model cuts the hardest part out of DNA origami, the decades-old technique for sculpting genetic material into nanoscale structures with medical and scientific uses.