Product ad New model · 30% lower credit cost
Gemini Omni 1.2 Flash
Use Gemini Omni 1.2 Flash on Gemini Omni, an independent AI platform that integrates leading video models. Make crisp AI videos up to 15 seconds long, edit them when you type a change, and upscale any clip to 1080p or 4K, all at about 30% less credits than Omni 1.1 Flash.
15-second clips Up to 4K 16:9 + 9:16
Preview16:9 · 4K
Gemini Omni 1.2 FlashDirected with Omni · 15 seconds
00:0700:15 Fit
ModelGemini Omni 1.2 Flash
Prompt
A tactile macro shot of a translucent glass speaker, neon rim light, slow dolly in, premium product film.
2 references Start frame Upload
9:1616:9
Estimated cost: 62 credits4K · 15s
Made with Omni
Community Creations
See how marketers and filmmakers use Gemini Omni 1.2 Flash to make 15-second product ads, chat-edited social clips, and character-led explainers.
Product ad
Character storyOne face. Six shots. A consistent brand world.
9:16 · 15s
Social clipA vertical hook with motion-tracked type.
9:16 · 4K
Brand filmCinematic lighting without a second render.
16:9 · 1080p
Dialogue sceneTwo characters, natural voice lines, one take.
16:9 · 15s
4K upscaleA rough draft carried to a clean final master.
16:9 · 4K01 / 06
What makes 1.2 different
Key Features of Gemini Omni 1.2 Flash
Gemini Omni 1.2 Flash handles text-to-video and image-to-video up to 15 seconds long, upscales any existing video to 1080p or 4K, and costs about 30% less at every resolution per generation.
01
00:15 / 00:154K
3s6s10s15s
01 / 05
Make 15-Second Clips in Up to 4K
Gemini Omni 1.2 Flash makes a single clip up to 15 seconds long from a text prompt or a starting image, on Gemini Omni's AI video generator. That is enough room for a complete product ad or a short scene with a beginning, middle, and end. You set any length from 3 to 15 seconds and any of four resolutions: 360p, 720p, 1080p, or 4K. Draft at 360p or 720p while you test ideas, since a 360p draft costs a small fraction of the same clip at 4K, then make the final at 1080p or 4K. You can also upscale any existing video up to 15 seconds long to 1080p or 4K with Gemini Omni 1.2 Flash.
02
Credits per renderOmni 1.1 Omni 1.2
4K
−30%
1080p
−30%
720p
−30%
360p
−30%
More variations. Less spend.
02 / 05
Pay About 30% Less at Every Resolution
Gemini Omni 1.2 Flash costs about 30% less than Omni 1.1 Flash at every resolution, from 360p drafts to 4K finals. The same credits that made 10 seconds of video with 1.1 go further with 1.2. In practice, that means you can make more versions of an ad, test more opening hooks, and keep more variations without draining your balance. Add 360p drafts and the standalone upscaler, and you spend real credits only on the clips you keep.
03
FaceProductStyleFrame AFrame B 10 refs
START
END
3 short video references supported
03 / 05
Multi-Modal References With Start/End Frames
Gemini Omni 1.2 Flash takes a start frame and an end frame, so you decide how the video opens and where it lands, and the model makes everything in between as one smooth move. It also takes up to 10 reference images and up to 3 short reference video clips alongside your text prompt. Use them to lock a product, a character's face, or a brand look so it stays the same from shot to shot. Google built 1.2 to follow image and video references more closely than 1.1, so products, characters, and brand details hold together across a whole campaign.
04
Edit with chatClip 04 · 12.4s
Make the neon sign warmer and move the camera 10% closer.
Applied lighting + camera change. Everything else preserved.
Now replace the bottle with the reference product.
Updating scene
Describe your next edit... Send
04 / 05
Conversational Video Editing
Conversational editing is the star of Gemini Omni 1.2 Flash. Upload a video up to 15 seconds long, up from 10 seconds on Omni 1.1 Flash, and describe the change in plain words: swap a character, replace a product, warm up the lighting, or change the camera angle. The model applies the change and keeps the rest of the scene, the motion, and the camera position the same. Each message builds on the last, so you refine a clip step by step instead of starting over.
05
NEW
DROP$29 Text follows the action
DROP$29 Text follows the action
Prompt
Put “NEW DROP” on the jacket and keep “$29” pinned to the product.
05 / 05
Accurate Text That Tracks Action
Connect on-screen text and graphics to the action in your video with a simple prompt. The text is spelled correctly and moves smoothly through the scene, so a title can follow a person or a price tag can stay stuck to a product as it moves. Put the exact words in your prompt, in quotes, and Omni 1.2 Flash places them cleanly inside the video. Keep each line short, because short quoted text comes out cleaner than a long sentence.
Prompt to final cut
How to Use Gemini Omni 1.2 Flash
Three simple steps from prompt to finished clip.
All modelsSearch⌕
Gemini Omni 1.2 Flash15s · 4K · references · audio
NewGemini Omni 1.1 Flash10s · 4K · start / end
Veo 3.1Cinematic video with audio
Pick the model
Open Gemini Omni's AI video generator and choose Gemini Omni 1.2 Flash from the model menu.
Reference
A slow dolly through a neon product studio, crisp reflections, shallow depth of field...
Face Product
Start End
Prompt and add references
Describe the scene you want, then add any reference images, a start and end frame, or a reference video.
Generating frame 72 / 360
Final quality pass84%
Configure and generate
Choose the length, resolution, and aspect ratio, then generate and download your clip.
Built for volume
15sper complete ideaBuilt for Fast, High-Volume Video Content
One model for the ideas you test, the campaign versions you ship, and the stories you keep telling.
Ideate, Animate, and Edit
Describe a short story in plain language, generate the first clip, and refine it by chatting, all without switching tools. With up to 15 seconds in one clip, a full idea fits in one generation instead of two stitched halves. Continue to the next shot while your look, characters, and pacing stay consistent. Because generation is fast and edits happen in chat, you move from idea to finished clip in one session, with sound made alongside the video.
Multilingual Social and Brand Content
Spin up localized versions of the same ad or social clip for different markets, then adjust the copy and scene by chatting. Landscape and vertical outputs (16:9 and 9:16) are ready for every platform, so one idea can fill your whole content calendar. With Omni 1.2 Flash costing about 30% less than 1.1, you can test more variations and keep posting without blowing the budget. Brand teams get the same product and colors in every version, because 1.2 follows reference images closely.
Character-Led Vlogs and Series
Pair Omni 1.2 Flash with Gemini Omni Characters to keep the same face, outfit, and style across every episode of a vlog or short series. Generate each episode quickly, then adjust wardrobe, setting, or action by chatting instead of starting over. A 15-second clip holds a complete moment of the story, and Extend Video tool carries it on when an episode runs longer. Voice lines sound natural, and two characters can hold a conversation in the same scene.
Explainer Content at Scale
For educational and explainer content, Omni 1.2 Flash's real-world knowledge and accurate on-screen text keep the facts and labels correct. Produce a batch of short lessons, product walkthroughs, or how-to clips with clear graphics and synced captions. Fifteen seconds is enough for one complete step, so each clip teaches one thing well. Low cost per clip makes it realistic to build a full library rather than a single video. When a lesson needs to look crisp on a big screen, upscale it to 4K before you publish.
Creator playbook
Tips for Best Results
Small prompt choices make a visible difference on the final render.
Lead with the scene, then edit
Generate a full base clip at 360p or 720p first, then use chat prompts for fixes. When a version is right, upscale that one clip to 1080p or 4K instead of paying for 4K on every try.
Keep your prompt simple
Lean on the model's world knowledge instead of over-describing every detail. Short, clear prompts get strong results, and you can add specifics through follow-up edits.
Use references the right way
Add a reference image for characters, products, or style, and keep video references to short clips. Combining reference types holds consistency across a scene better than text alone.
Put exact text in quotes
Write the on-screen words in quotes inside your prompt, and keep lines short and high-contrast. English comes out most reliably, so keep text-heavy shots brief.
Learn the model
Read More Get Insights from Experts
Get the insights you need. Our experts share actionable hacks, break down the hottest topics, and provide essential how-to guides to help you build, optimize, and scale.
PromptingModel guideWorkflowTrusted by creators
Loved by Creators
★★★★★ Excellent
I've tried many AI platforms, but the character consistency and image-to-video quality here are still the best.
JJan C. Trustpilot
The range of creative tools is excellent. Once you learn the workflow, the possibilities are genuinely surprising.
TTom G. Trustpilot
A very versatile AI studio with strong video models, consistent characters, and powerful editing controls.
KKlant K. Trustpilot
Helpful AI tools all in one place: generation, editing, references, and upscaling without multiple subscriptions.
SScorpy Trustpilot
Customer service is quick and helpful, and the platform keeps getting better with every new model.
RRichard M. Trustpilot
With so many AI platforms out there, this one stood out as a stellar choice for a creator workflow.
JJon S. Trustpilot
I've tried many AI platforms, but the character consistency and image-to-video quality here are still the best.
JJan C. Trustpilot
The range of creative tools is excellent. Once you learn the workflow, the possibilities are genuinely surprising.
TTom G. Trustpilot
A very versatile AI studio with strong video models, consistent characters, and powerful editing controls.
KKlant K. Trustpilot
Helpful AI tools all in one place: generation, editing, references, and upscaling without multiple subscriptions.
SScorpy Trustpilot
Customer service is quick and helpful, and the platform keeps getting better with every new model.
RRichard M. Trustpilot
With so many AI platforms out there, this one stood out as a stellar choice for a creator workflow.
JJon S. Trustpilot
Answers, without the wait
Frequently Asked Questions
Everything you need to know before your first Omni 1.2 render.
What is Gemini Omni 1.2 Flash?
Gemini Omni 1.2 Flash is Google's fast, low-cost video generation and editing model, part of the Gemini Omni family, and the name you pick in Gemini Omni's model menu. It makes clips up to 15 seconds long from text, images, and short video references, edits clips when you describe a change, and upscales videos to 1080p or 4K.
How is Gemini Omni Flash different from other AI video models?
It is built for speed and low cost per generation, which makes it a strong fit for high-volume work where you make many versions, alongside models like Veo 3.1, Seedance 2.5, and Kling 4.0 on Gemini Omni. Its standout is conversational editing: you refine a clip by describing changes instead of generating it again from scratch.
Can I upscale a video I already have with Gemini Omni 1.2 Flash?
Yes. Open Gemini Omni's AI video upscaler, pick Gemini Omni 1.2 Flash, and upload an MP4 or MOV clip up to 15 seconds long at 360p, 720p, or 1080p. Choose 1080p or 4K and download the sharper version.
How much does Gemini Omni 1.2 Flash cost?
Gemini Omni 1.2 Flash costs about 30% less than Omni 1.1 Flash at every resolution. The credit cost of each clip depends on its length and resolution, and Gemini Omni shows the cost before you generate. See current plans on the pricing page.
Is Gemini Omni Flash the same as Gemini 2.0 Flash?
No. Gemini Omni Flash is a dedicated video generation and editing model in the 2026 Gemini Omni family, and Gemini 2.0 Flash is an older language model.
What is new in Gemini Omni 1.2 Flash compared with 1.1?
Gemini Omni 1.2 Flash makes clips up to 15 seconds long instead of 10, edits videos up to 15 seconds long instead of 10, upscales any clip to 1080p or 4K as a standalone tool, and costs about 30% less at every resolution. Google also built it to follow image and video references more closely and to make more natural voice lines.
How long are Gemini Omni Flash videos?
Omni 1.2 Flash makes clips from 3 to 15 seconds long from a text prompt or a starting image. Clips made with a start and end frame, or with reference images and videos, run up to 10 seconds. On Gemini Omni, Extend Video adds to the end of any clip when a project needs more runtime.
Can I use image and video references with Gemini Omni Flash?
Yes. You can combine up to 10 reference images, up to 3 short reference video clips, and a text prompt in one generation to guide composition, character, and style. Keep video references short for the most reliable results.
How do I use the Gemini Omni video generator?
Gemini Omni 1.2 Flash runs on Gemini Omni through Google's direct API, with the model's full features. Open the AI video tools, choose Gemini Omni 1.2 Flash in the model menu, write your prompt, and generate. You will also find it in Edit Video, Extend Video, and Upscale Video.
What resolution does Gemini Omni 1.2 Flash output?
Gemini Omni 1.2 Flash has four resolution options on Gemini Omni: 360p, 720p, 1080p, and 4K, in 16:9 or 9:16. You can also upscale any finished clip to 1080p or 4K with the standalone upscaler.
Make Wonders.
Start Creating.
One prompt, one model, and a finished clip in a single focused workflow.
Draft fast. Finish in 4K.