Gemini App Enhances Photo-to-Video Creation with Visual Ingredients
Google has introduced a significant update to its Gemini app, enhancing the photo-to-video generation feature by incorporating visual ingredients. This new functionality allows users to upload up to three reference images to guide the Veo model within the app. These visual inputs can include characters, objects, styles, and scenes, facilitating:
– Character Consistency: Ensuring a character’s appearance remains uniform across various scenes or shots.
– Style Transfer: Applying specific textures, lighting, or artistic styles from a reference image to the entire video.
– World-Building: Aligning objects and scenes in the video to match a user’s custom-designed world.
For instance, users can now see characters from their reference images integrated into scenes, performing actions as specified by their prompts. This advancement aims to simplify the creation process by reducing the need for lengthy, complex prompts.
The rollout of this feature begins today, with full availability expected next week for subscribers of Google AI Plus, Pro, and Ultra. Additionally, Google has updated the Gemini app’s Tools menu on Android and iOS to specify the model used for video generation, now indicating Veo 3.1.
