Google just announced Veo 2, their advanced AI video generation model, along with Whisk for image creation. I signed up for the Veo 2 waitlist after seeing what it can do.
Veo 2 is Google’s latest text-to-video model, integrated into VideoFX. It creates high-definition videos with enhanced physics simulation and image rendering capabilities. The model shows notable improvements in video content understanding and generation quality, making it valuable for content creators and developers.
Whisk brings a fresh approach to image generation using Imagen 3. Rather than relying solely on text prompts, you can use existing images as references. The process works by inputting images that define your desired subject, scene, and style. Whisk combines Imagen 3 and Gemini to create new images based on these visual references.
The advanced editor in Whisk allows precise control through both text and source images across three main categories: subject, scene, and style. An additional input bar helps refine the final output to match your vision.
These tools add powerful options to creative workflows. The waitlist for Veo 2 is currently open, and Whisk is accessible through Google Labs.
For more insights on Google’s AI tools, check out my analysis of their recent Music FX DJ tool at https://adam.holter.com/music-fx-dj-googles-ai-music-tool-adds-real-time-sound-creation/
I’ll share updates as I test both tools. Share your experiences in the comments if you’ve tried them.
