Obnews Tech Desk: Google has made great improvements in video and image generation, taking its Artificial Intelligence (AI) technology to new heights. The American tech company has introduced its second generation video generation model Veo 2 and updated Imagen 3 image generation model. Along with this, Google has also launched a new experimental tool Whisk, which allows users to style and remix images.
Google Veo 2 models
The Veo 2 model is designed to improve the understanding of real-world physics, human motion and expression. This model can now produce more realistic videos, with finer details and better quality.
major features
- Resolution: Video generation up to 4K.
- Video Length: Extended for a few minutes.
- Ability to handle complex requests: Genre, lens type, and cinematic effects.
Veo 2 is integrated into Google Labs' video generation tool VideoFX. Users can join the waitlist for these new features by visiting Google Labs. Google plans to expand Veo 2 to YouTube Shorts and other products next year.
Imagen 3 Model
Google has also upgraded its Imagen 3 image generation model. The model can now render different art styles like photorealism, impressionism, abstract, and anime with greater accuracy.
improvement
- Ability to understand input prompts better.
- More detail and texture in the image.
- Facility to create images in different art styles.
This model will also be available through the ImageFX tool in Google Labs.
Click here to read other technology news
Whisk: new experimental tool
Whisk is a new tool from Google that combines the visual understanding and description capabilities of Imagen 3 and Gemini.
Features of Whisk
- Users can input images and remix them as per their choice.
- Gemini generates detailed captions for images, which are fed into Imagen 3.
- This process allows to generate unique images in different styles.
Comments are closed.