Gemini Omni 1.2 Flash (Image-to-Video)

Gemini Omni 1.2 Flash animates a picture into a 3-15 s video with sound; add a last frame for a smooth transition between two images.

Google Gemini Omni 1.2 Flash brings a picture to life: first_frame_image opens the video, and an optional last_frame_image closes it with a smooth transition between the two. Sound (dialogue, music and effects) is made with the video: 3 to 15 seconds from one picture, 3 to 10 seconds with a last frame, at 360p, 720p, 1080p or 4K.

Inputs: prompt (required: the motion, camera and sound), first_frame_image (required; JPEG, PNG, WebP or HEIF up to 20 MB), last_frame_image (optional), duration (default 5), resolution (720p by default), aspect_ratio (16:9 or 9:16; left out, it follows the picture) and seed.

It does not keep characters or products from reference images (use flymyai/gemini-omni-1_2-flash-ref2v) and does not edit a video (use flymyai/gemini-omni-1_2-flash-edit). Google refuses pictures of real public figures.

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): a picture is about 1,100 input tokens. 5 seconds at 720p cost about $0.36. A refused or failed run costs nothing.

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 (Image-to-Video) via API

curl -X POST https://api.flymy.ai/api/v1/flymyai/gemini-omni-1_2-flash-i2v/predict \
  -H "X-API-KEY: $FLYMYAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"prompt":"Slowly move the camera closer to the landscape, preserve its composition","first_frame_image":"https://images.unsplash.com/photo-1470770841072-f978cf4d019e?w=768&q=80&fm=jpg","duration":5,"resolution":"720p"}'

API documentation · Create a free account · Pricing

Related models