Gemini Omni 1.2 Flash: Fast and cost-effective with longer clips
Web page · https://deepmind.google/blog/gemini-omni-12-flash-fast-and-cost-effective-with-longer-clips
First seen by Oriel on .
AI summary
Google is rolling out Gemini Omni 1.2 Flash, a lower-cost video-generation model that creates clips up to 15 seconds and supports conversational editing with improved reference consistency.
- The model costs $0.07 per second for 720p video, 30% less than Gemini Omni 1.1; users can draft at 360p or 720p and upscale selected clips to 1080p or 4K.
- Users can set clip duration in one-second increments from 3 to 15 seconds and edit clips through follow-up prompts instead of regenerating them.
- Reference inputs can include images, motion clips up to three seconds, and audio cues; the model aims to preserve characters, products, styles, and scene details across frames and camera changes.
- Google says speech, lip-sync, multi-speaker conditioning, and continuous camera movements have improved, while fast sports action, rapid script changes, and complex physics remain areas of ongoing development.
- The model is generally available through the Gemini API and Gemini for business, with access also rolling out across Flow, Google Vids, the Gemini app, and Google Ads.
#generative video #gemini api #video editing #multimodal ai
Generated by gpt-5.6-sol. Check the original for details.
Aliases
| Source | External ID | URL |
|---|---|---|
| Google DeepMind Blog | https://deepmind.google/blog/gemini-omni-12-flash-fast-and-cost-effective-with-longer-clips/ | https://deepmind.google/blog/gemini-omni-12-flash-fast-and-cost-effective-with-longer-clips/ Read discussion |