Cut AI
Realistic Film Style
5sGemini Omni · Text to Video
Choose a mode and add the required media. T2V, I2V, and R2V create ten-second videos; Extend follows the source video.
Gemini Omni Generator
Gemini Omni
Upload
Upload 0 image(s) · JPEG / PNG / WebP · max 10 MB each
0/2000
Required Credits50
Gemini Omni Video Generation
Four Gemini Omni Workflows
Each mode maps to a documented FreeModel model ID and request shape.
gemini-omni-t2v creates a fixed ten-second video from a prompt with no image input.
Workflow
How to Create Videos with Gemini Omni
Choose a video mode, add your source material and review the output settings before you create.
Choose a Mode
Select text, source image, reference images, or source video. The corresponding model ID is selected automatically.
Add the Required Media
I2V needs 1–2 images, R2V needs 1–5 images, and Extend needs one video URL. T2V needs no upload.
Set Output Shape
Choose 720p or 1080p and 16:9 or 9:16. T2V, I2V, and R2V always use 10 seconds.
Generate for 50 Credits
Start the generation, follow its progress, then preview or download the completed MP4 video.
Text-to-Video, Image Animation and Video Extension
Choose the input contract that describes what you already have.
Start from Text
Describe the scene, motion, camera, lighting, and audio intent for a ten-second clip.
Gemini Omni FAQ
Answers describe the current FreeModel integration.
Which service powers this page?
Cut AI uses FreeModel's asynchronous video API and the four Gemini Omni model IDs documented there.
How much does one task cost?
Every Gemini Omni task currently costs 50 Cut AI credits.
How many images can I use?
I2V accepts one or two images. R2V accepts one to five images. Extend accepts up to five optional reference images.
What does Extend accept?
Extend requires a public source video URL and a prompt. Do not send a seconds field; the duration follows the source video.
Is the result immediate?
No. FreeModel returns a queued task. Cut AI polls the task and downloads the content after it reaches completed status.
Are hard masks supported?
No. The current Gemini Omni API contract exposes prompts and media references, not hard region masks.
Need help? Contact [email protected]
Create a Gemini Omni Video
Choose the input mode, add the required media, and submit a FreeModel task.
More AI Models
Explore another model for your next scene or image.
Seedance 2.5Longer scenes, flexible references and native audio.
Kling 4.0Guide 4–30 second scenes with image, video and audio references.
MiniMax H3Flexible inputs and 2K detail for 4–15 second shots.
Seedance 2.0Text, image and reference-guided video creation.
Nano Banana 2.1Create and refine images with visual references.
Seed Audio 1.0A voice workflow guide. Speech generation is not connected.
