Gemini Omni 1.2 Flash: Fast and cost-effective with longer clips

2026-11-10 · Google DeepMind

Gemini Omni 1.2 Flash launches with longer clips, lower cost

On November 5, 2026, Google DeepMind Product Manager Anish Nangia announced Gemini Omni 1.2 Flash. The model is generally available across the Gemini API, Google Cloud, and Gemini for business. It is designed for professional projects and scaled video production, adding native 15-second video creation, stronger reference adherence, multi-turn conversational editing, and a 30% price reduction.

Faster and more cost-effective at scale

  • 720p video is priced at $0.07 per second, 30% lower than Gemini Omni 1.1.
  • Teams can draft quickly at 360p or 720p, fix a detail with a follow-up edit instead of regenerating the entire clip, then upscale the best results to 1080p or 4K.

Longer clips and better reference adherence

  • Native generation and editing now supports up to 15 seconds, up from 10 seconds in Omni 1.1. Duration can be specified in one-second increments from 3 to 15 seconds.
  • The longer length is intended for complete stories, product explainers, or full social ad spots in a single generation.
  • Users can combine character, product, or style images, short motion clips up to three seconds, and audio cues. Omni 1.2 Flash holds those details from start to finish.
  • Faces, garments, packaging typography, and brand colors stay consistent across camera angles, making it easier to turn existing product photography or character sheets into virtual try-on clips, catalog spins, and branded video ads.
  • In one example, one model photo plus front-and-back product shots of three outfits produce a 15-second virtual try-on sequence across 360-degree turns and match cuts while preserving the model’s identity and each garment’s cut, drape, and back details.

More consistent results

  • The model maintains stronger character, object, and scene consistency from first to last frame, with less visual drift or morphing across motion and camera transitions.
  • This applies when interpolating between first and last keyframes or extending a clip to build a longer sequence; products, characters, props, and environments stay consistent from shot to shot.
  • In an example using the same static studio-lighting exhibition poster and a five-layer animation prompt, Omni 1.1 Flash did not match the reference as closely as 1.2. Omni 1.2 Flash builds the poster layer by layer on a dusty-pink cyclorama rising hexagonal plinth, assembling ribbed glass, warm filament, faceted crystal, and coiled-cord letterforms for HALO, GLOW, and LUMEN, and locking materials, shadows, and typographic details through the final frame.

Easier editing in conversation

  • Users can refine the same clip turn by turn, such as swapping a product or background, changing lighting or weather, or switching aspect ratio, instead of starting over.
  • Multi-turn conversational editing works across full 15-second clips, making it easier to produce ad variants for different audiences and placements without re-briefing or regenerating.
  • In one example, prompts swap the background turn by turn from a striped pavilion tent to an oak forest, a stable with a white horse, a market fair, and a stone castle while keeping both characters’ performances, armor reflections, and camera framing intact.

More natural speech

  • The model can generate more fluid, natural-sounding dialogue, clearer lip-sync, and distinct multi-speaker conditioning.
  • This applies to multi-character dialogue in Flow, video explainers in Gemini for business, and polished pro videos with avatars, music, and narration in Google Vids.
  • In an example conditioned on one conservatory scene image plus character, mouth, and one-second voice references, the model routes each sampled voice to the right character with expressive lip-sync and natural comedic timing across a 15-second animated scene.

More controllable, cinematic look

  • Users can direct complex continuous camera movements, including sweeping FPV flythroughs, dramatic zoom-outs, and orbits, with significantly fewer unwanted jump cuts, steadier scale, and a more polished cinematic look.
  • In one example, guided by two architectural reference photos, Omni 1.2 Flash directs one continuous FPV drone flight across the piazza, through the bronze doors, and up through the Pantheon’s coffered dome to the oculus with zero jump cuts.

Truncated ending

The original article ends with a section heading about longer clips, smoother motion, and tighter consistency. The sentence beginning “Gemini Omni 1.2 Flash generates clips up t” is truncated in the source, so the remaining details cannot be confirmed.

Source