Gemini Omni 1.1 Flash: Text to Video
Generate cinematic videos with audio from text prompts or reference images using Gemini Omni 1.1 Flash, supporting aspect ratio, resolution, and keyframe interpolation controls. Ideal for text-to-video storytelling, animating product shots or illustrations, and iterative conversational video editing.
Acerca de
This ComfyUI tutorial workflow turns a written prompt (and optionally a reference image) into a short, cinematic video using Google’s Gemini Omni 1.1 Flash via the GeminiVideoOmniV2 node. The node handles the API call to Gemini, then returns a generated clip and, when enabled, an accompanying audio track. You get direct control over aspect ratio and resolution so your outputs are ready for social, product pages, or widescreen edits.
Lo que proporcionas
- Leyendo el flujo de trabajo
Se ejecuta en ComfyUI. Este flujo de trabajo no puede ejecutarse en esta página. Ábrelo en Comfy Cloud con todo cargado o descárgalo para tu propio ComfyUI.
Probar en CloudPreguntas y respuestas
Open the GeminiVideoOmniV2 node and look for API/key configuration, or set the environment variable as documented by the custom node (then restart ComfyUI). If the node cannot find a key, the request will fail.
Yes. Connect a reference image to GeminiVideoOmniV2’s image/reference input. The model will use it to inform composition and style. Keep your prompt consistent with the image content for better visual continuity.
Use the aspect ratio and resolution settings in GeminiVideoOmniV2. Common choices are 16:9 for YouTube, 9:16 for vertical reels, and 1:1 for feeds. Match SaveVideo’s FPS to the generator’s FPS to preserve timing.
Increase keyframe interpolation in GeminiVideoOmniV2 to smooth transitions and stabilize subjects. Also keep prompts precise and avoid large prompt changes between iterations. Lowering resolution can reduce artifacts on slower hardware or networks.