E-MagazineGemini Omni 1.2 Flash can help you make 15-second AI videos from images and prompts at lower costs
Gemini Omni 1.2 Flash supports video generation up to 15 seconds, compared with five seconds less in the previous version.
Google claims improved character and product consistency, smoother camera movements, better lip-sync and multi-step conversational editing.
Video generation costs $0.07 per second for 720p output, making it 30% cheaper than Gemini Omni 1.1.
Search leader Google has announced it will be rolling out Gemini Omni 1.2 Flash for Gemini business users and the Gemini API. The AI model brings the capability to generate 15-second videos, 5 seconds longer than the previous iteration. The tech giant’s updated video generation tool costs 30 per cent less (compared to Gemini Omni 1.1) at $0.07/second for 720p output. Plus, it supports enhanced reference following and multi-step conversational editing.
Gemini Omni 1.2 Flash: Step-wise edits, improved consistency and more changes
According to a Google blog post, eligible users will have the option to draft lower-quality output (such as 360p or 720p), alter the output based on their liking via prompts. Once the desired output is achieved, they can consider exporting an upscaled version (4K or 1080p). Google claims the model will adhere to characters, products, images, short clips (up to 3 seconds), audio and more supplied to it.
“Faces, garments, packaging typography, and brand colours stay consistent across camera angles, making it easy to turn existing product photography or character sheets into virtual try-on clips, catalog spins, and branded video ads,” Google said. Further, Omni 1.2 Flash maintains better coherence in frames and “less visual drift or morphing”.
Gemini Omni 1.2 Flash is rolling out starting today to all Google AI subscribers. Refine videos through multi-turn conversational edits and enjoy sharper visual stability in the Gemini app. Plus, Google AI Ultra subscribers can now create and edit videos up to 15 seconds long, giving you more room to tell complete stories, create product explainers, or produce full social ad spots in a single generation. Learn more about Omni 1.2 Flash in our blog: https://t.co/WY9t7SwWFn
— Google Gemini (@GeminiApp) November 5, 2026
The model can also refine the same clip step-wise to change products, background, lighting, weather, aspect ratio and more. As for speech-based enhancements, the updated model offers “more fluid, natural-sounding dialogue, clearer lip-sync and distinct multi-speaker conditioning”. In a similar vein, complex and continuous camera movements will have fewer jump cuts and a more cinematic look.
Google noted Gemini Omni 1.2 Flash is now generally available for businesses, developers and creators across the company’s products and developer platforms. The output will have a SynthID watermark.
Gemini Omni 1.2 Flash: Availability
For eligible developers and businesses, it will be available in Google AI Studio (prototype) and the Google Cloud console. For others using Google apps, direct scenes and multi-turn edits will be available in Flow, and 15-second video generation in Google Vids with a Google or Workspace account and the Gemini app (for Google AI Ultra subscribers).
