Google unveils Veo, next-gen model for generating video
Veo is able to generate 1080p videos in a plethora of cinematic and visual styles, and those vids can go beyond a minute. Google says the generated video should closely represent your creative vision by accurately capturing a prompt’s tone and rendering details in longer prompts. The model understands terms like timelapse or aerial shots of a landscape. The video the AI created should be coherent and consistent and subjects move realistically throughout frames.
To further refine the model, Google has collaborated with filmmaker Donald Glover and is inviting a range of filmmakers and creators to experiment with Veo.
Veo is available to select creators in private preview in VideoFX by joining the waitlist. Google plans to bring Veo’s capabilities to YouTube Shorts in the future.
Imagen 3: Google’s text-to-image model gets a boost
Google has worked on enhancing the quality of its image generation model. Imagen 3 generates photorealistic, lifelike images, and doesn’t have as many artifacts when compared to previous models.
In fact, the images generated by Imagen 3 are incredible. Here are some of the examples shared by Google.
For the first image, we have the following prompt:
- A close up of a sleek wolf perched regally in front of gray background, in a high-resolution photograph with detailed fine details, isolated on a plain stock photo with color grading in the style of a hyper-realistic style.
Second image prompt:
- View from above of beautiful river canyon with trees, showcasing its stunning natural beauty with green mountains and blue waters. The photo captures the vastness of nature’s creation in the style of its creation.
Third image prompt:
- Three women stand together laughing, with one woman slightly out of focus in the foreground. The sun is setting behind the women, creating a lens flare and a warm glow that highlights their hair and creates a bokeh effect in the background. The photography style is candid and captures a genuine moment of connection and happiness between friends. The warm light of golden hour lends a nostalgic and intimate feel to the image.
It can even draw. It’s absolutely amazing how this drawing looks (it doesn’t look like generated by AI), and it was generated by the following prompt:
- Abstract sketch: A blur of expressive lines and energy captures the dynamic movement of a dancer in a gestural charcoal drawing. Sketch on aged parchment paper.
Just like Veo, Imagen 3 is available to select trusted testers by joining the waitlist.
Musicians are not left out
Google is partnering with musicians, songwriters, and producers for its development of generative music technologies, including Lyria, which is Google’s most advanced model for AI music generation.
Google is working on a suite of music AI tools like Music AI Sandbox. This will allow people to create instrumental sections from scratch or transform sounds.