Gemini Omni Flash is now available in OpenVideoMaker. The new integration gives creators one fast place to try prompt-only video, image-to-video, multi-image reference generation, and text-guided video editing. Open the new Gemini Omni Flash generator when you want to move from an idea, a portrait still, a small set of references, or a source clip into a generated video.
What is new
The new page supports four workflows. Text-to-video starts with only a prompt. Image-to-video uses one uploaded image as the visual anchor. Reference-to-video accepts multiple images and lets the prompt point to them with tags such as <IMAGE_REF_0>. Video edit mode accepts one video and a text instruction, then prices the request from the input video duration.
How to prompt it
Keep the first generation focused. Name the source, the main action, the camera move, and the final use case. For multi-image reference work, insert each image token directly into the prompt so the model knows which image should control visual details, mood, character, or scene layout.
Pricing preview
OpenVideoMaker now estimates Gemini Omni Flash cost in real time as you change duration or upload media. Text-only requests use the published text-to-video per-second estimate. Requests with image or video input use the multimodal per-second estimate, and video edit mode waits until the input video duration is known before showing the final estimate.
Try it
Start from Gemini Omni Flash, compare it with the broader AI Video Generator, or pair it with AI Image Generator when you need source stills before animation.