Models·
Google Launches Gemini Omni 1.2 Flash: Faster, Cheaper 15‑Second Video Generation
Gemini Omni 1.2 Flash adds native 15‑second video creation, multi‑turn editing, and a 30 % price cut, now generally available via the Gemini API and Google Cloud.
Google DeepMind has released Gemini Omni 1.2 Flash, a video generation model that now supports native 15‑second clips, multi‑turn conversational editing, and tighter reference adherence.
Key Enhancements
- Longer duration: clips up to 15 seconds, selectable in one‑second steps from 3 to 15 seconds.
- Cost reduction: pricing dropped 30 % to $0.07 per second for 720p output.
- Conversational edits: users can refine a clip with follow‑up prompts instead of full re‑generation.
- Improved consistency: characters, products, and brand elements stay stable across camera angles and motion.
The model is generally available through the Gemini API, Google Vids, and Gemini for Business, enabling production‑scale video pipelines at lower expense.
Why it matters for GPU / AI infrastructure: the lower per‑second cost and reduced re‑generation cycles translate into fewer GPU hours per project, helping teams optimize cloud compute budgets on platforms such as AiGpu.
- aigpu
- ai gpu
- ai gpu cloud
- aigpu dubai
- gemini
- video generation
- cloud ai
- google deepmind
By AiGpu Editorial · Editorial rewrite based on public reporting (Google AI Blog)
← All articles