Google has presented Veo 3.1, a new version of artificial intelligence model for video generation which promises greater realism and fidelity, as well as advances in notification adherence, levels of control and consistency when generating videos.
AI video generators like Veo and Sora highlight the controversial role that generative AI plays in the creative industries. Many videographers, filmmakers, and creators worry about how AI is trained with their existing footage and implemented by studios and streaming platforms. streaming. Heated debates and lawsuits are on the table, but the truth is that the AI majors continue to advance.
I see 3.1 and I see 3.1 Fast
Google claims that these new models can now generate better native audio, including natural conversations and synchronized sound effects. Additionally, developers can now take advantage of a better understanding of cinematic styles. The internet giant also claims that these models now maintain a greater character consistency in multiple scenes.
The new version of Veo will include some features that you may recognize if you’ve already used FlowGoogle’s AI movie creation program. The “Video Ingredients” feature will allow you to upload separate assets that Veo will combine into the final video. You will also be able to add objects to existing resources, and soon you will be able to delete them, a much-needed feature.
The company has also introduced new ways for developers guide them better Veo 3.1 models . First, they can provide up to three reference images of a character, object, or scene. This will allow the model to maintain greater consistency of the character across multiple shots.
Secondly, the new scene extension feature will allow developers to create longer videos by generating new clips that connect to the previous video. Previously, developers could only create 30-second videos. Creating two 30-second videos while maintaining character consistency was a daunting task, and with this new feature, each new video is generated from the last second of the previous clip to maintain visual continuity. Finally, developers can now provide a start and end image and ask Veo 3.1 to generate the transition between them along with the audio.
Developers can access the Veo 3.1 and Veo 3.1 Fast models through the Gemini API in Google AI Studio and Vertex AI. Users can access Veo 3.1 through both the Gemini and Flow apps.
