Google releases Gemini Omni 1.2 Flash with 30% cheaper video generation Google

Google launched Gemini Omni 1.2 Flash, expanding video generation clips up to 15 seconds and reducing generation costs by 30%. The model is available immediately via the Gemini API, Google AI Studio, Google Vids, and Flow.

The update lowers inference costs to zsh.07 per second of 720p video, pricing a 15-second generation at .05 compared to prior rates. The model adds conversational in-painting and editing, allowing users to alter backgrounds, camera angles, lighting, and aspect ratios without regenerating clips from scratch.

What it is

• Extended duration. Generates video sequences up to 15 seconds, up from the prior 10-second ceiling.
• Multimodal references. Accepts conditioning references across still images, short video snippets, and audio tracks to preserve character consistency and wardrobe across shots.
• Conversational editing. Users can prompt localized adjustments to lighting, camera motion, weather, and background elements interactively.
• Improved audio-visual sync. Enhances lip-sync accuracy for multi-character dialogue and smooths camera pans.
• Resolution pipelines. Generates natively in 360p or 720p with integrated upscaling up to 1080p and 4K.

Price

Sources

• Google: Introducing Gemini Omni 1.2 Flash