Gemini Omni 1.2 Flash — AI Video Model
Gemini Omni 1.2 Flash makes crisp AI videos up to 15 seconds long, edits them when you type a change, and upscales any clip to 1080p or 4K, all at about 30% less credits than Omni 1.1 Flash.
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.
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.
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 OpenArt'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.
Try it NowPay 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.
Try it NowMulti-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.
Try it NowConversational 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.
Try it NowAccurate 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.
Try it NowHow to Use Gemini Omni 1.2 Flash on OpenArt
Three simple steps from prompt to finished clip.
Pick the model
Open OpenArt's AI video generator and choose Gemini Omni 1.2 Flash from the model menu.
Prompt and add references
Describe the scene you want, then add any reference images, a start and end frame, or a reference video.
Configure and generate
Choose the length, resolution, and aspect ratio, then generate and download your clip.
Built for Fast, High-Volume Video Content
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.
Try it NowMultilingual 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.
Try it NowCharacter-Led Vlogs and Series
Pair Omni 1.2 Flash with OpenArt 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.
Try it NowExplainer 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.
Try it NowTips for Best Results
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.
Get Insights from Experts Blog
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.
Read More
Loved by Creators
I've tried many AI platforms... but OpenArt is still the best for character creation, image-to-video quality, and the variety of models available.
OpenArt offers an excellent array of AI tools... once you learn the features, the creative possibilities are amazing - and their support team is outstanding.
OpenArt is a very versatile AI platform with many image and video models, consistent character creation, and powerful editing tools.
Helpful AI tools all in one place - image and video generation, editing, and more... no need for multiple subscriptions.
Customer service is always quick and helpful... and the platform keeps getting better with new features and tools.
I've tried many AI platforms... but OpenArt is still the best for character creation, image-to-video quality, and the variety of models available.
OpenArt offers an excellent array of AI tools... once you learn the features, the creative possibilities are amazing - and their support team is outstanding.
OpenArt is a very versatile AI platform with many image and video models, consistent character creation, and powerful editing tools.
Helpful AI tools all in one place - image and video generation, editing, and more... no need for multiple subscriptions.
Customer service is always quick and helpful... and the platform keeps getting better with new features and tools.
I've tried many AI platforms... but OpenArt is still the best for character creation, image-to-video quality, and the variety of models available.
OpenArt offers an excellent array of AI tools... once you learn the features, the creative possibilities are amazing - and their support team is outstanding.
OpenArt is a very versatile AI platform with many image and video models, consistent character creation, and powerful editing tools.
Helpful AI tools all in one place - image and video generation, editing, and more... no need for multiple subscriptions.
Customer service is always quick and helpful... and the platform keeps getting better with new features and tools.
With so many AI platforms out there, OpenArt stood out as a stellar choice - I'd recommend it to any creator.
This platform includes everything you need for AI content creation - images, video, characters, audio, and multiple AI models in one place.
OpenArt is pushing the boundaries of AI video creation... and it's clear the team is committed to improving the creator experience.
I made my first AI music video with OpenArt... and their support team was the best help I've ever experienced.
I'm very happy with the support - my issue was resolved quickly and the team made the process easy.
With so many AI platforms out there, OpenArt stood out as a stellar choice - I'd recommend it to any creator.
This platform includes everything you need for AI content creation - images, video, characters, audio, and multiple AI models in one place.
OpenArt is pushing the boundaries of AI video creation... and it's clear the team is committed to improving the creator experience.
I made my first AI music video with OpenArt... and their support team was the best help I've ever experienced.
I'm very happy with the support - my issue was resolved quickly and the team made the process easy.
With so many AI platforms out there, OpenArt stood out as a stellar choice - I'd recommend it to any creator.
This platform includes everything you need for AI content creation - images, video, characters, audio, and multiple AI models in one place.
OpenArt is pushing the boundaries of AI video creation... and it's clear the team is committed to improving the creator experience.
I made my first AI music video with OpenArt... and their support team was the best help I've ever experienced.
I'm very happy with the support - my issue was resolved quickly and the team made the process easy.
Frequently Asked Questions
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 OpenArt'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.
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 OpenArt. Its standout is conversational editing: you refine a clip by describing changes instead of generating it again from scratch.
Yes. Open OpenArt'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.
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 OpenArt shows the cost before you generate. See current plans on the OpenArt pricing page.
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.
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.
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 OpenArt, Extend Video adds to the end of any clip when a project needs more runtime.
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.
Gemini Omni 1.2 Flash runs on OpenArt 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.
Gemini Omni 1.2 Flash has four resolution options on OpenArt: 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.