Gemini Omni 1.2 Flash降价增容

Google Deepmind has made its Gemini Omni 1.2 Flash video-generation model generally available. This updated model can create clips up to 15 seconds long, supports conversational editing, and costs 30 percent less than its predecessor. The model is rolling out through the Gemini API, Google AI Studio, the Google Cloud Console, Flow, Google Vids, the Gemini app for Google AI Ultra subscribers, and Google Ads. Every generated video carries a SynthID watermark. Clips can now run between three and 15 seconds, up from a maximum of 10 seconds previously, with pricing dropping to $0.07 per second for 720p video. Generated clips can also be edited through an ongoing conversation, allowing users to tweak the background, lighting, or aspect ratio without regenerating the entire clip. This feature works across the full 15-second length. A tiered workflow is used, with drafts created at 360p or 720p, followed by individual detail corrections and final upscaled results to 1080p or 4K. The model can take character images, product photos, short motion clips of up to three seconds, and audio cues as inputs, ensuring consistent faces, clothing, packaging typography, and brand colors across different camera angles. For example, it can generate a 15-second sequence with 360-degree turns while preserving the model's identity and each garment's cut and drape. Visual consistency has improved, with less visual drift or morphing across motion and camera transitions. The model also produces more fluid, natural-sounding dialogue with clearer lip-sync and the ability to distinguish between multiple speakers, handling complex camera movements with fewer unwanted jump cuts.