AI
Google releases Gemini Omni 1.2 Flash and cuts 720p video generation price by 30%
Google introduced Gemini Omni 1.2 Flash, now generally available in the Gemini API and enterprise Gemini. The new version supports native video generation up to 15 seconds, multi-turn conversational editing, and stronger reference adherence. The price of 720p video has dropped 30% from Omni 1.1 to $0.07 per second.
Google announced the launch of Gemini Omni 1.2 Flash, which is generally available in the Gemini API and Gemini for business. The version adds native 15-second video generation, multi-turn conversational editing, and enhanced reference-adherence capabilities. The price for 720p video is $0.07 per second, a 30% decrease from Gemini Omni 1.1.
Video duration has increased from Omni 1.1’s maximum of 10 seconds to 15 seconds, and users can specify durations from 3 to 15 seconds in 1-second increments. Google said this allows product explainers, complete social ads, and short films with full narratives to be completed in a single generation.
The new version can combine images of people, products, or styles, short motion clips of up to 3 seconds, and audio prompts to guide generation, while keeping faces, clothing, packaging fonts, and brand colors consistent across shot changes. Google also emphasized that the model can reduce visual drift or distortion during motion and camera transitions, making characters, objects, props, and scenes more stable in first and last frames and between shots.
For workflows, users can first draft quickly in 360p or 720p, then modify details through subsequent edits without regenerating the entire video, and finally upscale the finished work to 1080p or 4K. Multi-turn editing supports replacing products or backgrounds, adjusting lighting and weather, changing aspect ratios, and more, and can continue iterating on the full 15-second clip.