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

Deep-Image.ai - Image Upscaling, Background Removal, Avatars, Interiors, and Doodles

Deep-image.ai: Enhance images, create AI avatars, and transform backgrounds effortlessly with Deep Image AI. Try our services for free without the need for a credit card. Elevate your eCommerce visuals and reimagine real estate photography today.

428.2 K
Genmo AI: Create Videos and Images with Artificial Intelligence

Alpha.genmo.ai: Create stunning videos, 3D models, images, art, and beyond with Genmo AI, your ultimate creative companion.

453
Create Stunning Images with Stable Diffusion AI Technology

Tinybots.net: Create AI-generated images and photos with Stable Diffusion on Tinybots Artbot. Utilize a distributed computing cluster fueled by the AI Horde for seamless image generation. No login necessary, and completely free to use.

17.7 K
Methexis-Inc Img2prompt API on Replicate

Replicate.com: Generate text prompts that closely match an image with style using Methexis Inc's Img2Prompt tool. Optimized for stable-diffusion (clip ViT-L/14).

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