Apple Is Toying With an AI Image Editor
It’s unclear whether the project will make it to any Apple products, but you can try it out now on GitHub.
By Adrianna Nine February 9, 2024
https://www.extremetech.com/computing/a ... age-editor
With the help of researchers at the University of California at Santa Barbara (UC Santa Barbara), Apple has developed an AI-powered image editor that responds to text-based commands. A demo is now live on Hugging Face, though it’s unclear whether the project will ever make it to any Apple products.
Apple’s model is called MLLM-guided image editing, or MGIE, with MLLM being short for “multimodal large language models.” This jargon means MGIE leverages a large language model capable of mixing natural language processing with image inputs, which is vital for any AI-based image editor. Rather than using sliders, filters, and other manual image-editing tools, MGIE users can simply tap out a quick text prompt that tells the model what they want their result to look like.
Piers Morgan and Oprah Winfrey 'deepfaked' for US influencer's ads
10 hours ago
Celebrities including Piers Morgan, Nigella Lawson and Oprah Winfrey have criticised the use of AI deepfake online adverts that gave the false impression they had endorsed a US influencer's controversial self-help course.
The adverts promoted the so-called "Genie Script", the centrepiece of a "manifestation" course sold for $37 (£29) a time by Wesley "Billion Dollar" Virgin.
He describes himself as a motivational coach who has 1.1 million followers on Instagram and claims to be worth $40m.
The videos, used to lure buyers to purchase the product, claim the Genie Script is a "missing" Hebrew Bible scripture of just 20 words that could - supposedly - change your life.
Its promotion blends pseudo-science, conspiracy theories and the manipulation of celebrity likenesses - all to draw in customers desperate for the chance to take control of their fate.
BREAKTHROUGH – Los Alamos Generates AI Pictures Without Using a Random Picture to Start
February 27, 2024 by Brian Wang
https://www.nextbigfuture.com/2024/02/b ... start.html
Los Alamos national lab made an artificial intelligence framework called Blackout Diffusion generates images from a completely empty picture. The machine-learning algorithm, unlike other generative diffusion models, does not require initiating a random seed to get started.
The results are comparable to DALL-E or Midjourney, but require fewer computational resources than these models.
Diffusion models create samples similar to the data they are trained on. They work by taking an image and repeatedly adding noise until the image is unrecognizable. Throughout the process the model tries to learn how to revert it back to its original state.
An important unique aspect of Blackout Diffusion is the space it works in. Existing generative diffusion models work in continuous spaces, meaning the space they work in is dense and infinite. However, working in continuous spaces limits their potential for scientific applications. Blackout Diffusion means that entirely new types of images can be created by AI.
New AI image generator is 8 times faster than OpenAI's best tool — and can run on cheap computers
News
By Keumars Afifi-Sabet
published 30 minutes ago
https://www.livescience.com/technology/ ... -computers
Scientists used "knowledge distillation" to condense Stable Diffusion XL into a much leaner, more efficient AI image generation model that can run on low-cost hardware.
