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

Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifold

Introduction

What is DragGAN?

DragGAN is a powerful tool for interactive point-based manipulation on the generative image manifold. It allows users to "drag" any points of the image to precisely reach target points in a user-interactive manner.

How does DragGAN work?

DragGAN consists of two main components: 1) a feature-based motion supervision that drives the handle point to move towards the target position, and 2) a new point tracking approach that leverages the discriminative GAN features to keep localizing the position of the handle points.

Features of DragGAN

  • Precise control over where pixels go, thus manipulating the pose, shape, expression, and layout of diverse categories such as animals, cars, humans, landscapes, etc.
  • Ability to deform an image with realistic outputs even for challenging scenarios such as hallucinating occluded content and deforming shapes that consistently follow the object's rigidity.
  • Can be used for image manipulation and point tracking tasks.

Price

The paper and code are available for free, and the images, text, and video files on the site are made freely available for non-commercial use under the Creative Commons CC BY-NC 4.0 license.

Drag - Alternative

Retouch4me — Advantages of Artificial Intelligence (AI) in Retouching

Our Plugins Are Designed to Work the Same Way a Professional Retoucher Would. Retouch4me Preserves the Original Skin Texture and Makes Photos Look Natural. You Just Need to Upload Your Photos to the Plug-In, Click a Button, and Wait for AI to Get the Job Done.

273.3 K
RunDiffusion - Automatic1111 in the Cloud

Fully managed Automatic1111, Fooocus, and ComfyUI in the cloud on blazing fast GPUs. No code. Get a private workspace in 90 seconds. Start creating AI Generated art now!

332.3 K
FeedHive - Create content at scale ⚡

Create, publish, and easily manage your social media content at scale with FeedHive's AI-powered platform

57.3 K
Brilliant Labs

Pocket-sized AR for imaginative hackers. At Brilliant Labs, we're building an open-source ecosystem to support developers and creatives reimagining the future.

112.8 K
More Tags about: Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifold