Google is enhancing its photo and video products by integrating generative AI features, starting with YouTube Shorts. Creators can generate new video elements using text prompts and photos. YouTube introduces easily applied generative effects and a centralized AI playground hub for creators. The current rollout relies on the Veo 2 model, with plans to transition to the more advanced Veo 3 model in the future. At present, these features are limited to users in the United States, Canada, Australia, and New Zealand, with expansion to more countries anticipated.
Google is implementing generative AI features across its photo and video products, beginning with YouTube Shorts, focused on enhancing creator tools with new video elements.
YouTube creators will soon generate videos from a text prompt or use a photo as the basis for new generative AI videos, with easily applied effects accessible through the Shorts camera.
The current AI features utilize the Veo 2 model, which is less advanced than the recently introduced Veo 3; however, enhancements are planned to follow.
Initially available in the United States, Canada, Australia, and New Zealand, generative AI features for YouTube Shorts will later extend to more international markets.
Collection
[
|
...
]