Google Introduces Veo 2 AI Video Generation Model, Improves Imagen 3 Model

Google unveiled the successor to the Veo video generation model on Monday. Dubbed Veo 2, the artificial intelligence (AI) model improves on the capabilities of the older model which was launched in early 2024. Veo 2 can now generate videos in up to 4K resolution and for a much longer duration. The new model was introduced just a week after the Mountain View-based tech giant added Veo to Vertex AI for its enterprise clients. Veo 2 is currently only available to a select number of creators in the VideoFX platform via Google Labs.

Google Launches Veo 2 With Improved Capabilities

In a blog post, the tech giant detailed the new video-generation AI model. Currently, the older Veo AI model is available to users via Vertex AI and VideoFX, and it is also being used in the video background generator feature for YouTube Shorts. Now, the company introduced Veo 2, which is said to have achieved state-of-the-art results during internal testing, beating video models such as Sora.

The tech giant claimed that Veo 2 has made improvements in the detail and realism of the generated videos. Additionally, the AI model can now understand the language of cinematography. This means users can specify a genre, lens, cinematic effects, and camera movements and Veo 2 can generate videos to the exact specifications.

Highlighting an example, the post said Veo 2 can understand complex prompts such as “a low-angle tracking shot with 18mm lens that glides through the middle of a scene”. The mention of the lens will let the AI know that the user wants to generate a wide-angle shot which the lens is known for, the company added.

Additionally, Veo 2 can generate videos up to 4K resolution and can extend video duration to “minutes” in length. The company did not specify the maximum duration of videos that can be generated using the AI tool. The tech giant also claimed that the video model reduces the instances of hallucination and unwanted details such as extra fingers, morphed limbs, or unexpected objects will be seen less frequently.

On safety, Google stated that the company has added the native SynthID watermark on generated videos to help identify AI videos from real videos, reducing its misuse to create deepfakes. The company has also planned a gradual rollout of the AI model to control its access and improve its quality and safety before global availability.

Currently, Veo 2 is available to select users in VideoFX via Google Labs. Those interested in trying out the tool are asked to sign up for the waitlist. Further, the tech giant plans to expand Veo 2 to YouTube Shorts and other products next year.

Imagen 3 Also Rolling Out Globally in ImageFX

Alongside the introduction of Veo 2, the tech giant also rolled out the AI image generation model Imagen 3 in ImageFX to more than 100 countries. The latest iteration of the model has received several upgrades, including the ability to render more diverse art styles, greater accuracy, and better-composed images.

Imagen 3 also displays better prompt adherence and can render more details and textures in images, the company claimed. It is said to also excel in particular styles such as photorealism, impressionism, abstract, and anime.