Gemini Omni 1.2 Flash Now Generally Available with Enhanced Features and Lower Pricing
Gemini has announced the general availability of Gemini Omni 1.2 Flash, a significant update to its AI-powered video generation platform. This new version introduces several key features that improve upon previous versions, including native 15-second video creation, multi-turn conversational editing capabilities, and enhanced reference following.
The most notable change is the ability to generate videos up to 15 seconds long, an increase from the 10-second limit of its predecessor, Gemini Omni 1.1. This allows users to create more comprehensive stories and product explainers in a single generation.
Another significant improvement is the reduced pricing for Gemini Omni 1.2 Flash. The cost has been lowered by 30% compared to Gemini Omni 1.1, with prices starting at $0.07 per second for 720p video. This makes it an even more attractive option for businesses and developers looking to produce high-quality videos at scale.
The workflow of Gemini Omni 1.2 Flash is designed to keep costs down by allowing users to draft quickly in lower resolutions such as 360p or 720p, fix minor details with follow-up edits instead of regenerating the entire clip, and then upscale their best creations to higher resolutions like 1080p or 4K.
One of the key features of Gemini Omni 1.2 Flash is its ability to hold references together better than previous versions. Users can guide generation by combining character, product, or style images, short motion clips (up to three seconds), and audio cues, which are then maintained consistently throughout the video.
This improved reference following allows for more accurate and consistent results, particularly in scenarios where characters, objects, and scenes need to stay consistent across multiple frames. For example, users can create virtual try-on sequences with 360-degree turns and match cuts while keeping model identities and garment details intact.
Gemini Omni 1.2 Flash also introduces multi-turn conversational editing capabilities, which enable users to refine the same clip turn by turn without starting over from scratch. This feature is particularly useful for producing ad variants for different audiences and placements without re-briefing or regenerating entire clips.
Another significant improvement in Gemini Omni 1.2 Flash is its ability to generate scenes with more natural-sounding dialogue, clearer lip-sync, and distinct multi-speaker conditioning. Users can direct multi-character dialogue in Flow, create video explainers in Gemini for business, or produce polished videos with avatars, music, and narration in Google Vids.
Gemini Omni 1.2 Flash also allows users to control complex camera movements like sweeping FPV flythroughs to dramatic zoom-outs and orbits with significantly fewer unwanted jump cuts, steadier scale, and a more polished cinematic look. This is achieved by guiding the generation process using architectural reference photos or other visual cues.
The platform’s ability to generate longer clips with smoother motion and tighter consistency has been improved in Gemini Omni 1.2 Flash. Users can scroll through generated videos to see characters, text, and camera moves stay consistent across longer shots, multiple turns, and transitions without cuts.
Gemini Omni 1.2 Flash is now generally available across the Gemini API and Gemini for business, backed by Google Cloud’s enterprise-grade infrastructure and security. Provisioned Throughput is also available, and outputs carry an imperceptible SynthID watermark.
Discussion
No messages yet. Be the first to write.