Google started distribution of personal access Veo and Imagen 3 to generative AI models. Starting today, customers of the company’s Vertex AI Google Cloud suite can start using it Wow create videos from text prompts and images. Then, starting next week, Google will make Imagen 3, its latest text-to-image framework, available to those users.
With the introduction of Veo, Google said it is the first hyperscale cloud provider to offer an image-to-video model. In this respect, OpenAIs Sora the model is still only available to select artists, academics and researchers – though that could change quickly with the company Teasing 12 days of product demos from December 5.
Veo’s Google says the model produces “consistent and consistent” 1080p footage and can run for “over a minute.” The tool is capable of working with both text prompts and images. In the latter case, it is possible to use either artificial intelligence or human-generated images as a starting point for the video.
Looking at the sample images shared by Google, it’s clear that Veo, like all AI models, can struggle with cause and effect. For example, in a toasted marshmallow clip, the sweets do not turn yellow or char because they are exposed to the heat of the campfire. Artifact is also a problem, as you can see if you look closely at the hands in the concert footage.
As for Imagen 3, Google says the model “creates the most realistic and high-quality images from simple text prompts, surpassing previous versions of Imagen in terms of detail, lighting and artifact reduction.” Here again, you don’t have to look too closely to see that Google has more to do.
In the first example of a group of friends sitting in the trunk of a car, the original instruction mentions “flash photography,” but the subjects are clearly lit. One could argue that a flash was used to create strong backlighting, but if the idea behind the proposal was to create something representative of flash photography from the 1960s, this image is not.
However, Google wants to attract more of its enterprise customers using generative artificial intelligence. Citing his own researchthe tech giant says that among companies using generative AI in manufacturing, they report an 86 percent increase in revenue. However, a recent Appen survey From 2023 to 2024, the return on investment from AI projects decreased by 4.6 percentage points.
If you buy something through a link in this article, we may earn a commission.
