Education

A new paper proposes a method to protect the work of artists from being incorporated into Stable Diffusion, by using adversarial data perturbations to adversely affect generated results. Though the method even works with the image-to-image method of Stable Diffusion, it may require concerted public and organizational will to implement at scale – in common with many other proposed ‘data poisoning’ methods of this kind.

A new paper from researchers at Sony AI levels broad and scathing criticism at standards and practices in dataset re-use and abuse – but the cure might stop the computer vision sector’s current rapid rate of progress dead in its tracks.

A new system from Spain offers Stable Diffusion users the chance to truly control their compositions, by orchestrating multiple models into a single image inside the latent space.

New research indicates that Stable Diffusion, Google’s Imagen, and other latent diffusion systems and GANs are capable of replicating training data almost exactly. The findings may have implications in forthcoming legal cases that claim generative AI is ‘stealing’ the intellectual property of artists.

A new academic collaboration, including contributors from Microsoft, has developed an improved technique capable of fitting user-submitted images into a ‘deepfake puppetry’ workflow in only thirty seconds, with notably improved fidelity to the original identity..

A new academic collaboration, including contributors from Microsoft, has developed an improved technique capable of fitting user-submitted images into a ‘deepfake puppetry’ workflow in only thirty seconds, with notably improved fidelity to the original identity..

A new research collaboration between Poland and the UK may offer the first effective method to obtain a much-cherished ‘holy grail’ of deepfake image synthesis research – the ability to generate temporally coherent human video from latent diffusion systems such as Stable Diffusion.

Google Research has revealed a new type of framework for text-to-image synthesis, based on the Transformers architecture, rather than latent diffusion.

A new academic collaboration, including contributors from Microsoft, has developed an improved technique capable of fitting user-submitted images into a ‘deepfake puppetry’ workflow in only thirty seconds, with notably improved fidelity to the original identity..