Google has launched Gemini Omni Flash, a new multimodal video-generation model from DeepMind that creates and edits video conversationally from image, audio, video, and text inputs, with SynthID watermarking on by default.

Google's new multimodal AI model powers updates to Flow and Flow Music, including conversational video editing and AI-generated media tools.

The model marks Google's bid to collapse the multimodal generative stack — text-to-image, image-to-video, video-to-video, audio generation — into a single foundation model with a…