Gemini Omni 1.1 Flash: Image to Video
Generate videos from text prompts or reference images using Gemini Omni 1.1 Flash, a multimodal model that handles text-to-video, image-to-video, keyframe interpolation, and iterative video editing with natural language. Outputs a single MP4 video with optional audio, supporting aspect ratios, resolutions up to 4K, and scene extension. Ideal for cinematic storytelling, product visualization, and rapid video prototyping.
试试一个示例
关于此工作流
This ComfyUI tutorial workflow shows how to turn a text prompt or a single still image into a finished MP4 clip using Gemini Omni 1.1 Flash. The core of the pipeline is the GeminiVideoOmniV2 node, which accepts a prompt and (optionally) a reference image to drive image-to-video generation. You can target common aspect ratios and resolutions up to 4K, set clip duration and frame rate, and enable optional audio. The included MarkdownNote provides inline tips, while SaveVideo writes the final video to disk.
Technically, the flow is simple and robust: LoadImage brings in the provided blue_studio_car.png (or your own asset) and feeds it to GeminiVideoOmniV2 when you want image conditioning. The model handles text-to-video and image-to-video, along with internal keyframe interpolation and scene extension, controlled through your prompt and node parameters. GeminiVideoOmniV2 returns the generated clip, and SaveVideo outputs a single MP4 with your chosen fps and path. Leave the image input disconnected for pure text-to-video; connect it to anchor motion, style, and composition to your reference.
常见问答
No. Connect LoadImage to GeminiVideoOmniV2 for image-to-video, or leave it disconnected for text-to-video. Using a reference image helps lock style, layout, and subject appearance.
The workflow supports up to 4K, but start with lower resolutions and shorter durations for fast iteration. Higher resolution, longer clips, or higher fps will take longer to generate.
Yes, optional audio can be enabled if exposed by the GeminiVideoOmniV2 node. If audio is returned, SaveVideo will include it in the MP4; otherwise, the clip will be silent.
Update ComfyUI, verify your internet connection, and ensure the GeminiVideoOmniV2 node has valid API credentials if required. Reduce resolution/duration for tests, then scale up.