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.
Technically, GeminiVideoOmniV2 is the generator: you provide the prompt and any reference image, set visual parameters, and adjust keyframe interpolation to smooth motion and maintain subject continuity between beats. The SaveVideo node then encodes the frames (and audio, if present) to a file. Because the graph is compact—GeminiVideoOmniV2 feeding into SaveVideo—you can iterate quickly: tweak the prompt, adjust aspect ratio or interpolation strength, re-queue, and compare results for fast creative refinement.
API
從程式碼使用此工作流
每個 Comfy 工作流都是一個 JSON 圖。下方的 payload 就是此工作流，與 ComfyUI 執行時完全相同 — 你可以從此 URL 取得、放入版本控制，或在 ComfyUI 載入並逐節點執行。
使用 Comfy SDK 以 TypeScript 或 Python 執行。相同程式碼可用於 Comfy Cloud 或你自架的 ComfyUI — 只需更改 base URL。
// Install (beta)
npm i @comfyorg/sdk
// Run this workflow (TypeScript)
import { Comfy } from "@comfyorg/sdk";
const client = new Comfy({ apiKey: "comfyui-..." });
const wf = await client.workflows.fromFile("workflow_api.json");
const job = await client.run(wf);
await job.getOutputs("<output-node-id>")[0].toFile("output.png");SDK 需使用 API 格式的工作流：請在 ComfyUI 開啟此工作流，並使用 檔案 → 匯出工作流（API）。
