Attempting to make precise compositions with latent diffusion generative image models such as Stable Diffusion can be like herding cats; the very same imaginative and interpretive...
Google Research, it seems, is attacking text-based image-editing from a number of fronts, and, presumably, waiting to see what ‘takes'. Hot on the trail of this...
Anyone who has learned Italian learns early to pay attention to context when describing a broom, because the Italian word for this mundane domestic item has...
This week two new, but contrasting AI-driven graphics algorithms are offering novel ways for end users to make highly granular and effective changes to objects in...
Opinion Of late, the deepfake detection research community, which has since late 2017 been occupied almost exclusively with the autoencoder-based framework that premiered at that time...
The image synthesis research sector is thickly littered with new proposals for systems capable of creating full-body video and pictures of young people – mainly young...
The most well-known line of inquiry in the growing anti-deepfake research sector involves systems that can recognize artifacts or other supposedly distinguishing characteristics of deepfaked, synthesized,...
Ironically, Stable Diffusion, the new AI image synthesis framework that has taken the world by storm, is neither stable nor really that ‘diffused' – at least,...
The release of stability.ai's Stable Diffusion latent diffusion image synthesis model a couple of weeks ago may be one of the most significant technological disclosures since...
Findings from a new paper indicate that state-of-the-art AI is significantly less able to recognize and interpret AI-synthesized images than people, which may be of concern...
New research out of China offers an effective and novel method for restoring detail and resolution to user-uploaded video that is automatically compressed on platforms such...
Researchers from China have developed a new AI-based image enhancement system that's capable of making images of a person more ‘beautiful', based on a novel approach...
New research from Columbia university suggests that the safeguards that prevent image synthesis models such as DALL-E 2, Imagen and Parti from being able to output...
A new research paper from Harvard University suggests that OpenAI's headline-grabbing text-to-image framework DALL-E 2 has notable difficulty in reproducing even infant-level relations between the elements...
Researchers from Michigan State University have devised a way for synthetic faces to take a break from the deepfakes scene and do some good in the...