Grok Imagine just got a powerful new way to create videos You can now choose exactly how each uploaded image is used: • First frame • Intermediate frame • Last frame • Loop • Reference Instead of giving Grok one image and hoping for the best, you can now control how a scene starts, evolves and ends Reference images can guide: • Style • Characters • Products • Scenes • Overall visual direction This feels much less like simply generating a video....and much more like directing one From a single idea to an entire scene

Grok Imagine just got a really powerful new editing feature You can now edit text directly inside an image Posters, ads, event invites, menus, graphics.....instead of regenerating the whole image just because one word is wrong, you can simply change the text right there this fixes one of the most annoying problems with AI-generated visuals

Grok Imagine (@imagine) has seen many improvements lately, among them the new image model 2.0, and start-frame / end-frame support for video. But a little birdie has told me that the major new video model "Imagine 2.0" is yet to come (soon), and that it will be incredible! 🔮

Grok Imagine created this beautiful video of the good old Manhattan skyline and the World Trade Center created from an image generated by Image 2.0. In memory of the most beautiful towers New York ever had and the victims of the 9/11 attacks.