The Kling O3: Video Edit workflow is designed to provide a seamless video editing experience by integrating advanced AI capabilities. This workflow allows users to upload a video and a reference image, leveraging the Kling O3 model to perform precise subject editing and scene composition. The workflow is structured around several key nodes: LoadVideo, LoadImage, and KlingOmniProEditVideoNode. The LoadVideo node is responsible for importing the video file, while the LoadImage node allows users to input a reference image that guides the editing process. The KlingOmniProEditVideoNode is the core of this workflow, utilizing the Kling O3 model to apply sophisticated edits that ensure both visual coherence and audio-visual synchronization are maintained throughout the video.
API
Use this workflow from code
Every Comfy workflow is a JSON graph. The payload below is this workflow, exactly as ComfyUI runs it — fetch it from the URL, keep it in version control, or load it in ComfyUI and run it node by node.
Run it from TypeScript or Python with the Comfy SDK. The same code targets Comfy Cloud or a ComfyUI you host yourself — only the base URL changes.
// Install (beta)
npm i @comfyorg/sdk
// Run "Kling O3: Video Edit" (TypeScript)
import { Comfy } from "@comfyorg/sdk";
const client = new Comfy({ apiKey: "comfyui-..." });
// This workflow, exported in API format (see note below)
const wf = await client.workflows.fromFile("api_kling_o3_video_edit_api.json");
const asset = client.assets.fromFile("input.png");
wf.setInput("17", "image", asset); // LoadImage
const job = await client.run(wf);
await job.getOutputs("14")[0].toFile("output.png"); // SaveVideoThe SDK takes a workflow in API format: open this workflow in ComfyUI and use File → Export Workflow (API).
Comfy Cloud API access requires a plan with an API key.
FAQ
