Drag Your GAN vs Midjourney

Drag Your GAN lets you reshape a generated image by dragging handle points to target spots on the canvas. Instead of training on labeled pose data or 3D priors, DragGAN moves pixels inside a pretrained GAN's image manifold so edits stay photorealistic even when occluded regions get hallucinated. The project page hosts the SIGGRAPH 2023 paper, demo clips, and links to open source code.

Most GAN editors rely on fixed training annotations or 3D meshes, which limits what you can deform. DragGAN pairs feature-based motion supervision with discriminative point tracking so handle points follow your cursor while staying on the object surface. That makes it useful for nudging animal poses, facial expressions, car angles, and landscape layouts without retraining the generator.

Researchers, graphics students, and computer vision engineers use it to prototype interactive image editing workflows. The Max Planck Institute page distributes the paper PDF and GitHub repo under a non-commercial Creative Commons license, with contact details for the lead author.

Midjourney is an image and video generation model you use through the midjourney.com web app, with community galleries on Explore and support routed through Discord. Version 8.2 is the current release, and the careers site describes ongoing work on both creative models and separate research projects.

Compared with general-purpose image APIs, Midjourney sells aesthetic control and community curation rather than raw throughput alone. Paid tiers add Relax mode for unlimited slower generations, Stealth mode to keep work private on Pro and Mega, and tiered Fast GPU hour pools that refresh monthly.

The company calls itself a community-funded research lab of about 60 people, with offices in San Francisco, London, and New York. It targets artists, designers, marketers, and hobbyists who want stylized images and short videos without running their own GPU stack.