awesome-repositories.com
Blog
MCP
awesome-repositories.com

Discover the best open-source repositories with AI-powered search.

ExploreCurated searchesOpen-source alternativesSelf-hosted softwareBlogSitemap
ProjectMCP serverAboutHow we rankPress
LegalPrivacyTerms
© 2026 Bringes Technology SRL·VAT RO45896025·hello@awesome-repositories.com
XingangPan avatar

XingangPan/DragGAN

0
View on GitHub↗
35,822 stars·3,419 forks·Python·25 viewsvcai.mpi-inf.mpg.de/projects/DragGAN↗

DragGAN

DragGAN is an interactive generative AI editor and GAN image editing tool designed for modifying the shape and structure of objects within images. It functions as a latent space manipulator that enables precise geometric and appearance editing by transforming images into editable latent codes.

The system provides a web-based visual dashboard for real-time manipulation. Users can change the appearance of generated objects through an interactive point-based dragging interface, utilizing a process where source and target coordinates drive the optimization of the generative model.

The project includes capabilities for real image inversion, allowing standard photographs to be converted into latent representations for editing. This process is supported by a toolset for latent space optimization and gradient-driven point tracking to ensure the rendered image evolves according to user-defined constraints.

Features

  • Point-Based Manipulation - Provides an interactive point-based dragging interface to control the shape and structure of objects in images.
  • Latent Space Generative Models - Manipulates compressed latent representations via gradient descent to achieve specific geometric and appearance changes.
  • Point Tracking - Uses gradient-driven point tracking to precisely shift image pixels toward user-defined target locations.
  • GAN Inversion - Enables the transformation of real photographs into latent representations to allow interactive editing of non-generated imagery.
  • Generative Adversarial Image Synthesis - Implements a GAN-based synthesis architecture to generate and manipulate high-resolution realistic images.
  • Real Image Inversion - Converts standard photographs into a format that can be edited using generative adversarial network tools.
  • Latent Inversion - Transforms real photographs into editable latent codes through a generator input optimization process.
  • Generative AI - Offers a creative environment for performing AI-driven transformations of the shape and structure of objects in images.
  • Human-in-the-Loop Tools - Provides a real-time interaction loop that allows users to guide the generative process through direct visual feedback.
  • Graphics & Design - Assists in graphic design by allowing the reshaping of visual elements without manual redrawing.
  • Interactive Dashboards - Implements a web-based interface that organizes visual components for real-time image manipulation.
  • Generative Editing Dashboards - Ships a web-based visual dashboard for the real-time manipulation of generated imagery.
  • Image Editing and Manipulation - Point-based interactive manipulation of generative image manifolds.
  • Image Generation Models - Interactive point-based manipulation for generative image manifolds.
  • Interactive Drag Editing - Interactive point-based manipulation on generative manifolds.

Star history

Star history chart for xingangpan/dragganStar history chart for xingangpan/draggan

How this analysis was created: This summary and feature list are AI-generated from collected project material and can contain mistakes. Stars, license and language are imported from GitHub. Inclusion does not mean that we have tested or audited this project. Check the source documentation for any feature you depend on. Learn more on our About page.

AI search

Explore more awesome repositories

Describe what you need in plain English — the AI ranks thousands of curated open-source projects by relevance.

Start searching with AI

Projects sharing features with DragGAN

These projects share indexed features with DragGAN. Shared tags can include platform or build tooling; verify the primary use case before treating a result as a replacement.
  • opengvlab/dragganOpenGVLab avatar

    OpenGVLab/DragGAN

    4,952View on GitHub↗

    DragGAN is an interactive generative image editor and manipulator that allows users to reshape visual output by moving handle points on a generative network manifold. It functions as a tool for point-based image editing, mapping user-defined coordinate shifts to a generative model's latent space to deform images. The system includes a generative image inversion tool that converts real photographs into latent representations. This process enables the interactive manipulation of non-generated content by bringing real-world images into a compatible format for the generative adversarial network.

    Pythondraggangradio-interfaceimage-editing
    View on GitHub↗4,952
  • nvlabs/styleganNVlabs avatar

    NVlabs/stylegan

    14,412View on GitHub↗

    StyleGAN is a TensorFlow-based generative adversarial network framework designed for the synthesis of high-resolution synthetic imagery. It utilizes a style-based generator architecture to create realistic visual assets from latent vectors, focusing on the production of high-fidelity images. The system incorporates style mixing and stochastic noise injection to control visual attributes and fine-grained details. It uses adaptive instance normalization and progressive resolution upsampling to manage image quality and variety across different resolutions. The framework covers the full lifecycl

    Python
    View on GitHub↗14,412
  • eriklindernoren/pytorch-ganeriklindernoren avatar

    eriklindernoren/PyTorch-GAN

    17,472View on GitHub↗

    PyTorch-GAN is a research-oriented framework providing a collection of modular implementations for generative adversarial network architectures. It serves as a toolkit for training and evaluating models that utilize adversarial minimax optimization to produce synthetic data, offering a structured environment for exploring complex generative tasks within the PyTorch ecosystem. The library distinguishes itself through a comprehensive suite of image synthesis and manipulation capabilities, including super-resolution, inpainting, and cross-domain style translation. It supports advanced training m

    Python
    View on GitHub↗17,472
  • junyanz/iganjunyanz avatar

    junyanz/iGAN

    4,007View on GitHub↗

    iGAN is a framework for producing synthetic images using generative adversarial networks. It provides a web-based interface for interactively creating and editing imagery across categories such as landscapes, architecture, and fashion using pre-trained models. The system enables precise control over visual output through latent space exploration, interpolation, and projection. Users can guide the generative process using an interactive editor featuring sketching, coloring, and warping brushes to refine specific regions or shapes in real-time. The project supports both automated scripted gene

    Python
    View on GitHub↗4,007
Compare all 30 related projects→

Frequently asked questions

What does xingangpan/draggan do?

DragGAN is an interactive generative AI editor and GAN image editing tool designed for modifying the shape and structure of objects within images. It functions as a latent space manipulator that enables precise geometric and appearance editing by transforming images into editable latent codes.

What are the main features of xingangpan/draggan?

The main features of xingangpan/draggan are: Point-Based Manipulation, Latent Space Generative Models, Point Tracking, GAN Inversion, Generative Adversarial Image Synthesis, Real Image Inversion, Latent Inversion, Generative AI.

Which projects share features with xingangpan/draggan?

Projects with overlapping indexed features include: opengvlab/draggan — DragGAN is an interactive generative image editor and manipulator that allows users to reshape visual output by moving… nvlabs/stylegan — StyleGAN is a TensorFlow-based generative adversarial network framework designed for the synthesis of high-resolution… eriklindernoren/pytorch-gan — PyTorch-GAN is a research-oriented framework providing a collection of modular implementations for generative… junyanz/igan — iGAN is a framework for producing synthetic images using generative adversarial networks. It provides a web-based… nvlabs/stylegan2-ada-pytorch — This project is a PyTorch implementation of a generative adversarial network designed for high-resolution image… paddlepaddle/paddlegan — PaddleGAN is a generative AI framework and deep learning computer vision library built on the PaddlePaddle framework.…