#DragGAN

InternGPT introduces a unique visual interaction system using pointing devices, enhancing ChatGPT's efficiency in vision-centric tasks. Utilizing the Husky model, it specializes in multi-modal dialogues and visual scenarios, allowing for image editing and generation, and more. Community-driven, it continually evolves, promising improved functionalities and user experiences.

Discover DragGAN's point-based interaction for easy image editing on generative manifolds. Utilizing GAN capabilities, it provides flexible control and intuitive editing. With straightforward installation on CUDA devices and Apple Silicon, the project is accessible and compatible with Docker and pre-trained models. The GUI supports editing both GAN-generated and real images through GAN inversion. Compatible with PyTorch, it significantly advances image manipulation technology.