Imagine Video 1.5 launched last month as our best video model yet, with more lifelike motion and sound. Today it goes even further with text-to-video support, image and voice references, and native 1080p.
https://t.co/OWP5rCxlru
Announcing Grok 4.5, our first model trained specifically for coding and agents. It was trained with Cursor and offers frontier intelligence at leading speeds and cost efficiency.
https://t.co/i8HpU7w64k
Grok-Imagine-Video-1.5-Preview (720p) has landed #1 in the Image-to-Video Arena!
This is a massive +52 pt improvement over Grok-Imagine-Video (720p), surpassing the best video models Seedance-2.0 and HappyHorse.
Congrats to @xAI and @elonmusk on this big achievement!
We just added Grok's new imagine model in Paper so you can explore images even faster.
Here's what we found:
- Super fast generations for the quality
- Saves details when editing
- Perfect for 30 rapid experiments or chains of edit prompts
Available today, check it out!