Gemini Omni 1.2 Flash: Fast and cost-effective with longer clips

Gemini Omni 1.2 Flash, Google's latest video-generation model, makes clips both longer and cheaper to produce. A single generation can now run up to 15 seconds, up from 10 seconds with Omni 1.1, and Google has cut the price 30% from Omni 1.1 to $0.07 per second of 720p video (Google blog). Omni generates and edits video from a mix of inputs, including text prompts, images of characters, products or styles, motion clips up to three seconds long, and audio cues. Google says this is also the first time Omni is generally available. It is offered through the Gemini API and Google Cloud, where customers can reserve capacity through Provisioned Throughput.

Google's case for lower costs also rests on not regenerating whole clips. A user can draft at 360p or 720p, fix one detail with a follow-up instruction, such as swapping a product or background or changing the lighting, and then upscale the chosen version to 1080p or 4K. This turn-by-turn editing, where each instruction changes the clip produced by the previous one, now works across full 15-second clips, and clip length can be set in one-second steps from 3 to 15 seconds.

The quality claims are Google's own and are shown through examples it chose, including side-by-side comparisons with Omni 1.1, rather than measured results. Google says faces, garments, packaging text and brand colors now stay consistent across camera angles, with less drift from the first frame to the last, clearer lip-sync and fewer unwanted jump cuts. It also says development is ongoing on fast sports action, rapid script changes and complex physics. Every output carries SynthID, a watermark Google describes as imperceptible.