Google recently announced the launch of two new AI tools, Veo and Imagen 3, at its annual developers conference, Google I/O, held on May 14, 2024. These tools are designed to enhance video and image generation capabilities using advanced AI models.
Veo is Google's latest video generation model that can create high-quality 1080p videos from text prompts. It is designed to understand cinematic concepts like "timelapse" and "aerial shots," enabling it to produce videos that align with a filmmaker's vision. Veo has been showcased in collaboration with filmmaker Donald Glover and his creative studio, Gilga, highlighting its potential in professional filmmaking. Currently, Veo is available to select creators through a private preview on VideoFX.
Veo example
Imagen 3 is Google's most advanced text-to-image model to date. It can generate photorealistic images with intricate details and fewer visual artifacts compared to previous models. Imagen 3 excels in interpreting complex text prompts and can produce images in various styles, from detailed wildlife portraits to dynamic landscapes. This model is available for select creators in a private preview on ImageFX and will soon be integrated into Vertex AI.
Both Veo and Imagen 3 utilize Google's SynthID technology, which embeds digital watermarks into AI-generated content to ensure authenticity and traceability. This feature helps users identify if an image or video was generated by Google's AI tools.
These announcements signify Google's continued investment in generative AI technologies, aiming to support creative processes across various industries. By offering these tools to select creators initially, Google seeks feedback to refine their capabilities before broader release.
