Google is looking to the future with all its AI announcements at Google I/O. But Gemini improvements aren't the only interesting thing Google announced. Additionally, the company announced Veo and Imagen 3, generative AI tools aimed at bringing creative visions to life.
Google unveils next-generation video generation model Veo
Veo can produce 1080p videos in a variety of cinematic and visual styles, and those videos can be over a minute long. According to Google, the generated video should accurately capture the tone of the prompt and render the details of the longer prompt to faithfully express the creative vision. The model understands terms such as time-lapse and aerial landscape photography. AI-created videos should be consistent and coherent, with subjects moving realistically throughout the frame.
To further refine the model, Google is working with filmmaker Donald Glover to invite different filmmakers and creators to experiment with Veo.
Veo can select creators in a private preview on VideoFX by joining the waitlist. Google plans to bring Veo features to YouTube Shorts in the future.
Image 3: Google's text-to-image model gets better
Google has been working to improve the quality of its image generation models. Imagen 3 produces photorealistic images with fewer artifacts than previous models.
In fact, the images produced by Imagen 3 are incredible. Here are some examples shared by Google:
The first image displays the following prompt:
- Close-up of a sleek wolf sitting proudly in front of a gray background. A high-resolution photo with detailed details, isolated on a plain stock photo with color grading in a surreal style.
Second image prompt:
- View from above over a beautiful river gorge filled with trees, showing the amazing natural beauty of green mountains and blue water. This 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 in the foreground slightly out of focus. The sun sets behind the woman, with lens flare and a warm glow highlighting her hair and creating a bokeh effect in the background. The photography style is candid and captures moments of genuine connection and happiness between friends. The warm light of golden hour gives the image a nostalgic and intimate feel.
You can also draw pictures. This drawing looks really amazing (doesn't look like it was generated by AI) and was generated by the following prompt:
- Abstract Sketch: Expressive lines and blurs of energy capture the dynamic movement of a dancer in a gestural charcoal drawing. Sketch on an old cookie sheet.
Like Veo, Imagen 3 allows you to select trusted testers by joining a waiting list.
Musicians are not excluded either.
Google partners with musicians, songwriters, and producers to develop music generation technology, including Lyria, Google's cutting-edge model for AI music generation.
Google is working on a suite of music AI tools like Music AI Sandbox. This allows you to create instrument sections from scratch and transform sounds.
