It turns an image of a human into animated 3D models.

You can generate and edit icons and illustrations. It combines text prompt and fine-tuning with parameters.

A phenomenal exploration of generative experiments history in computer art by Amy Goodchild.

It allows to select any part of an image and add any object here or just automatically extend the whole scene (how it works and what it can do). It's one of the best implementations of algorithm-driven design features in a design tool — it's built into existing workflow, it's not a separate mode. Other tools like ClipDrop Uncrop caught up quick to do the same thing.

It can change color schemes of complex vector-based illustrations.

It can change an object on a photo with precise control over where pixels go, thus manipulating the pose, shape, expression, and layout of diverse categories such as animals, cars, humans, landscapes, etc.

To date, most digital image and video editing tools have been canvas-centric. Advances in artificial intelligence, however, have started a shift toward more object-centric workflows. Luke Wroblewski several examples of this transition.

A sketch-to-image tool by Stable Diffusion makers that converts a simple drawing into a dynamic image (more about it).

Ogilvy agency extended Johannes Vermeer’s painting “The Milkmaid” with DALL-E 2 for “La Laitière” brand.

Another Sensei experiment that puts graphic assets on top of raster packaging mockups. See more MAX 2022 announces (Instant Add, Magnetic Type, Motion Mix and Made in the Shade are the best).