Gemini Omni 1.2 Flash (Video Extend)
Gemini Omni 1.2 Flash continues a video by 3-10 seconds with matching motion, characters and sound.
Google Gemini Omni 1.2 Flash continues a video: it reads the last 10 seconds and adds 3 to 10 new seconds with matching motion, characters and sound. The result is the input (up to its last 30 seconds) with the new part at the end. Describe how the scene goes on, e.g. "The camera pans to the mountains"; reference_images can bring in a new character or object.
Inputs: prompt (required), video (required; MP4 or MOV of any length, up to 50 MB), reference_images (optional, up to 2), duration (seconds to add, 3-10, default 5), resolution (720p by default) and aspect_ratio.
It does not add content before or inside the video, cannot add new dialogue to an uploaded video in which someone speaks, and does not edit what is there (use flymyai/gemini-omni-1_2-flash-edit).
Price: per second of video by resolution, $0.024 at 360p, $0.07 at 720p, $0.105 at 1080p and $0.209 at 4K, plus the input and thinking tokens Google reports ($1.50 and $9.00 per 1M tokens), charged for the added seconds only: the video Google reads costs about $0.009 a second at 720p. Adding 5 seconds at 720p to a clip of 10 seconds or more costs about $0.45. A refused or failed run costs nothing.
- Text to Video
Price: From $0.024 per second of duration, depending on resolution; input tokens $1.50 per 1M, text and thinking tokens $9.00 per 1M. One run with default settings costs $0.35.
Run Gemini Omni 1.2 Flash (Video Extend) via API
curl -X POST https://api.flymy.ai/api/v1/flymyai/gemini-omni-1_2-flash-extend/predict \
-H "X-API-KEY: $FLYMYAI_API_KEY" \
-H "Content-Type: application/json" \
-d '{"prompt":"The camera slowly pulls back to reveal the whole scene","video":"https://storage.googleapis.com/open-inference-results/agent-files/1585/40ecb0fd73ed4b5eb3b34b53b3b7e290/bytedance-seedance-2_0-fast-text-to-video_a64b.mp4","duration":5,"resolution":"720p"}'API documentation · Create a free account · Pricing