Gemini Omni 1.1 Flash is live in ComfyUI via Partner Nodes. Google's multimodal video model, one node, five task types: → text-to-video → im…

Gemini Omni 1.1 Flash is live in ComfyUI via Partner Nodes. Google's multimodal video model, one node, five task types: → text-to-video → image-to-video → reference-to-video → edit → extend Up to 4K. Audio generated with every clip. Editing is conversational — "make this anime," "change the lighting," "change the sign to say Omni Flash." It applies the change and leaves the rest alone. Stack edits and it carries context from the last pass. Extend a clip and it reads the prior motion, lighting, and character identity to keep continuity through the new footage. Select "Omni Flash 1.1" in the Gemini Video Omni node and go. Click the link below to run the workflow ⬇️ Media

Source: ComfyUI (X) | 2026-08-28