Over the past year, Google has made progress in enhancing the quality of generative media technologies, thereby announcing the introduction of Veo, the latest and most advanced video generation model, alongside Imagen 3, the highest-quality text-to-image model yet.
Veo generates high-quality 1080p resolution videos in a wide range of cinematic and visual styles that can go beyond a minute. With an advanced understanding of natural language and visual semantics, it generates video that closely represents a user’s creative vision, accurately capturing a prompt’s tone and rendering details in longer prompts.
The model provides an unprecedented level of creative control and understands cinematic terms like ‘timelapse’ or ‘aerial shots of a landscape.’ Veo creates footage that is consistent and coherent, so people, animals, and objects move realistically throughout shots.
Here’s a preview offilmmaker Donald Glover and his creative studio, Gilga, who experimented with Veo for a film project:
Veo builds upon years of our generative video model work, combining architecture, scaling laws and other novel techniques to improve quality and output resolution. Veo is now available to select creators in private preview in VideoFX.
Whereas moving towards Imagen 3, over the last year, Google has made incredible progress in improving the quality and fidelity of its image generation models and tools. Imagen 3, the highest quality text-to-image model, generates an incredible level of detail, producing photorealistic, lifelike images with far fewer distracting visual artefacts than prior models.
For example, users can prompt Imagen 3 to give them a close-up of a sleek wolf perched regally in front of a grey background, in a high-resolution photograph with detailed fine details, isolated on a plain stock photo with colour grading in the style of a hyper-realistic style.
The result would be as follows:
/socialsamosa/media/post_attachments/727c5b99c9c1e9a17399b25d14d267ab69386269a23f1afa4c135fdb5db18b9e.webp)
Imagen 3 better understands natural language and the intent behind prompts, incorporating small details from longer prompts. The model’s capability opens up possibilities for generating personalized birthday messages, title slides in presentations, and more. Just like Veo, Imagen 3 is now available to select creators in private preview in ImageFX and by joining the waitlist.
Source: Social Samosa
