CADABRA AI

Gemini Omni 1.2: a 47-year story ad, in three shots

What Gemini Omni 1.2 is

Google's video model. Write in words what happens, attach pictures of the characters, and get a video of up to 15 seconds with sound born together with the picture.

Why 1.2 is better than the previous version

A clip of up to 15 seconds instead of 10, editing a clip of up to 15 seconds, a lower price, and more faithful reference pictures according to Google.

Characters first, as pictures

Three pictures on Nano Banana 2.1, one credit each: the girl in 1979, the same girl at 55, and her father.

Three shots on Omni 1.2

The dance and the tape that snaps, the headphones coming back in 2026, and the room turning back into 1979. Each shot 10 seconds at 720p, with the exact prompt.

Six things every good prompt repeats

A role for every reference, times in brackets, one continuous shot, write the sound, No music when you add a song, and text goes on in the edit.

Gemini Omni 1.2 questions

What is the difference between Gemini Omni 1.2 and 1.1?

A clip of up to 15 seconds instead of 10, editing a clip of up to 15 seconds, and a lower price: 5 seconds at 720p costs 4 credits instead of 6. According to Google it is also more faithful to reference pictures.

What did this ad cost?

27 credits: three character pictures at one credit each, and three 10-second shots at 720p.

How do I keep the same character across shots?

Make the character as a picture first, attach it to every shot, and give it a role in the first line of the prompt.

How many reference pictures can I attach?

Up to 10 pictures and up to 3 short clips.

Keep going


Home · Pricing · What's new · All engines · All effects · Help center · Lessons · Meital Sela · AI video · AI images · AI voice · AI music · Image to video · What it costs · Credits, not a subscription · Blog · Connect to Claude and ChatGPT · Presets · Privacy · Terms

Cadabra AI · Meital Sela · Rehovot, Israel