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.
API
Use este workflow a partir do código
Todo workflow Comfy é um grafo JSON. O payload abaixo é este workflow, exatamente como o ComfyUI executa — obtenha-o pela URL, mantenha-o no controle de versão ou carregue-o no ComfyUI e execute nó por nó.
Execute a partir de TypeScript ou Python com o Comfy SDK. O mesmo código serve para o Comfy Cloud ou um ComfyUI hospedado por você — apenas a URL base muda.
// 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");O SDK utiliza um workflow no formato API: abra este workflow no ComfyUI e use Arquivo → Exportar Workflow (API).
O acesso à API do Comfy Cloud requer um plano com chave de API.
