Google Unveils Veo 2 Video Generation Model, Expands VideoFX Access and Updates Imagen 3

Highlights

• Google introduces the updated Veo 2 model that enhances realism in generated videos.
• It includes features like creative prompts and an invisible SynthID watermark.
• Also unveils an upgraded Imagen 3 model for brighter images, better composition, richer textures and accurate rendering.
• It is now available globally via ImageFX.
• Google Labs’ new experiment Whisk allows users to prompt with images.

Google has announced its latest video generation model Veo 2 along with updates to the Imagen 3 image model and a new Whisk experiment. All tools highlight advancements in Google’s AI tools including Gemini.

Here’s a quick introduction to the new tools.

Google Veo 2 – What’s New?

The updated Veo 2 model comes with improvements in “understanding real-world physics and the nuances of human movement and expression,” making its generated videos more realistic and detailed.

Users can also add creative prompts to customize their videos. For example:

• “Low-angle tracking shot that glides through the middle of a scene.”
• “Close-up shot on the face of a scientist looking through her microscope.”
• Add “18mm lens” for a wide-angle shot.
• Use “shallow depth of field” to blur the background and focus on a subject.

Google also notes that Veo 2 “hallucinates less frequently” and includes an invisible SynthID watermark to ensure content transparency.

Veo 2 is being rolled out to VideoFX in Google Labs and access is expanding, although there’s still a waitlist. Google confirmed it will be integrated into YouTube Shorts and other products next year.

Google blog says, “We have been intentionally measured in growing Veo’s availability, so we can help identify, understand and improve the model’s quality and safety while slowly rolling it out via VideoFX, YouTube and Vertex AI.”

Veo 2 Demos

The Video Prompt (As shared with the above video on Google Deepmin) – “The camera floats gently through rows of pastel-painted wooden beehives, buzzing honeybees gliding in and out of frame. The motion settles on the refined farmer standing at the center, his pristine white beekeeping suit gleaming in the golden afternoon light. He lifts a jar of honey, tilting it slightly to catch the light. Behind him, tall sunflowers sway rhythmically in the breeze, their petals glowing in the warm sunlight. The camera tilts upward to reveal a retro farmhouse with mint-green shutters, its walls dappled with shadows from swaying trees. Shot with a 35mm lens on Kodak Portra 400 film, the golden light creates rich textures on the farmer’s gloves, marmalade jar, and weathered wood of the beehives.”

The Video Prompt (As shared with the above video on Google Deepmin) – “This medium shot, with a shallow depth of field, portrays a cute cartoon girl with wavy brown hair, sitting upright in a 1980s kitchen. Her hair is medium length and wavy. She has a small, slightly upturned nose, and small, rounded ears. She is very animated and excited as she talks to the camera.”

The Video Prompt (As shared with the above video on Google Deepmin) – “A low-angle shot captures a flock of pink flamingos gracefully wading in a lush, tranquil lagoon. The vibrant pink of their plumage contrasts beautifully with the verdant green of the surrounding vegetation and the crystal-clear turquoise water. Sunlight glints off the water’s surface, creating shimmering reflections that dance on the flamingos’ feathers. The birds’ elegant, curved necks are submerged as they walk through the shallow water, their movements creating gentle ripples that spread across the lagoon. The composition emphasizes the serenity and natural beauty of the scene, highlighting the delicate balance of the ecosystem and the inherent grace of these magnificent birds. The soft, diffused light of early morning bathes the entire scene in a warm, ethereal glow.”

The Video Prompt (As shared with the above video on Google Deepmin) – “A cinematic shot captures a fluffy Cockapoo, perched atop a vibrant pink flamingo float, in a sun-drenched Los Angeles swimming pool. The crystal-clear water sparkles under the bright California sun, reflecting the playful scene. The Cockapoo’s fur, a soft blend of white and apricot, is highlighted by the golden sunlight, its floppy ears gently swaying in the breeze. Its happy expression and wagging tail convey pure joy and summer bliss. The vibrant pink flamingo adds a whimsical touch, creating a picture-perfect image of carefree fun in the LA sunshine.”

Imagen 3 Update

Google has also introduced an upgraded Imagen 3 model, which delivers brighter images with better composition, richer textures and more accurate rendering of diverse art styles.

The Google announcement post said, “It can now render more diverse art styles with greater accuracy — from photorealism to impressionism, from abstract to anime.”

The updated model is now rolling out globally to ImageFX image tool from Google Labs, to more than 100 countries.

Examples of Imagen 3 creations —

Whisk Experiment

Google Labs is launching a new experiment called Whisk. Whisk allows users to prompt with images and is designed to demonstrate Imagen 3’s improvements alongside Gemini’s visual understanding and description capabilities.

Google describes it: “Under the hood, Whisk combines our latest Imagen 3 model with Gemini’s visual understanding and description capabilities. The Gemini model automatically writes a detailed caption of your images, and it then feeds those descriptions into Imagen 3. This process allows you to easily remix your subjects, scenes and styles in fun, new ways.”

FAQS

Q1. What improvements does the Veo 2 model bring to video generation?

Answer. The updated Veo 2 model improves “understanding real-world physics and the nuances of human movement and expression,” making generated videos more realistic and detailed. It also includes an invisible SynthID watermark to ensure content transparency.

Q2. How can users customise their videos using Veo 2?

Answer. Users can add creative prompts to customize their videos, such as “low-angle tracking shot,” “close-up shot on the face of a scientist,” and specify lens types like “18mm lens” for wide-angle shots or “shallow depth of field” to blur the background and focus on a subject.

Q3. What new features does the updated Imagen 3 model offer?

Answer. The upgraded Imagen 3 model offers brighter images, better composition, richer textures, and more accurate rendering of diverse art styles.

Q4. What is Google’s Whisk experiment?

Answer. Whisk is a new experiment by Google Labs that allows users to prompt with images. It demonstrates the improvements in Imagen 3 alongside Gemini’s visual understanding and description capabilities.

Read More: Google to Soon Integrate Text-to-Image Generator Imagen into Gboard Android App

Read More: Google Bard Global Updates: Image Generation