SPG
scinexx - das wissensmagazinKI-System ermöglicht Bildmanipulation für Laien. Intuitive Veränderung digitaler Bilder durch „DragGAN“ erleichtert auch Deep Fakes. #KI #DragGAN #GAN #KuenstlicheIntelligenz #DeepFake #Bildmanipulation
https://www.scinexx.de/news/technik/ki-system-ermoeglicht-bildmanipulation-fuer-laien/
Inautilo#Design #Projects
DragGAN · A surprising new method for manipulating generated images https://ilo.im/13eikn
_____
#AI #ImageEditing #DragGAN #DigitalDesign #UiDesign #WebDesign #GraphicDesign
Henrik SundströmPretty amazing #AI image manipulation. Check out the videos here: https://www.theverge.com/2023/5/19/23729633/ai-research-draggan-manipulate-images-click-and-drag
#DragGAN
#DragGAN
aœGezielte, „KI“-gestützte Bildbearbeitung.
@heiseonline stellt #DragGAN vor – technisch beeindruckend.
Dieses Verfahren dürfte für Designer und Fotografen erheblich interessanter (möglicherweise auch bedrohlicher) sein, als die eher schwer zu steuernde generative Komplett-Bilderstellung.
Mal sehen, wie #Adobe darauf reagiert…
Sascha Pallenberg 🇹🇼 ♻️ ⚡So sieht das Ende von #Photoshop bzw. den Profis aus, die damit so ziemlich jedes Photo passend gestalten konnten!
Nennt sich #DragGAN & macht euch alle in Sekunden zu absoluten Bildmanipulationsprofis. Ich finds erschreckend!
Marcel SIneM(S)US#DragGAN: KI-gestützte, fotorealistische Bildbearbeitung per Drag & Drop | heise online https://www.heise.de/news/DragGAN-Ist-KI-gestuetzte-Drag-Drop-Bildbearbeitung-die-Zukunft-von-Photoshop-9060667.html #ArtificialIntelligence
tomasz🚀Narzędzie #ai, które urywa łeb🤯
Więcej o projekcie → https://vcai.mpi-inf.mpg.de/projects/DragGAN/
Źródło → https://youtu.be/L5BjZUplYy8
Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifold
Synthesizing visual content that meets users' needs often requires flexible and precise controllability of the pose, shape, expression, and layout of the generated objects. Existing approaches gain controllability of generative adversarial networks (GANs) via manually annotated training data or a prior 3D model, which often lack flexibility, precision, and generality. In this work, we study a powerful yet much less explored way of controlling GANs, that is, to
JRT 
Drag Your #GAN: Interactive Point-based Manipulation on the Generative Image Manifold
"Through #DragGAN, anyone can deform an image with precise control over where pixels go, thus manipulating the pose, shape, expression, and layout of diverse categories such as animals, cars, humans, landscapes, etc."
Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifold
Synthesizing visual content that meets users' needs often requires flexible and precise controllability of the pose, shape, expression, and layout of the generated objects. Existing approaches gain controllability of generative adversarial networks (GANs) via manually annotated training data or a prior 3D model, which often lack flexibility, precision, and generality. In this work, we study a powerful yet much less explored way of controlling GANs, that is, to
.Wow, was für ein Tool! Es erlaubt punktuelle Manipulationen des Bildes mit hervorragenden Ergebnissen. Schaut's euch unbedingt das Video an! 😆
Projektvorstellung, mit vielen weiteren Beispielen:
https://vcai.mpi-inf.mpg.de/projects/DragGAN/
Der Code soll noch im Juni veröffentlicht werden.
Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifold
Synthesizing visual content that meets users' needs often requires flexible and precise controllability of the pose, shape, expression, and layout of the generated objects. Existing approaches gain controllability of generative adversarial networks (GANs) via manually annotated training data or a prior 3D model, which often lack flexibility, precision, and generality. In this work, we study a powerful yet much less explored way of controlling GANs, that is, to