The 'Kling O3: Reference to Video' workflow is designed to transform a reference image into a character-consistent video, offering precise storyboard control and native audio output. This workflow leverages the Kling O3 model, renowned for its ability to maintain character consistency across frames while integrating optional audio or text prompts for enhanced narrative depth. Technically, the workflow begins with the LoadImage node, which allows users to upload a reference image. The KlingOmniProImageToVideoNode is the core of this workflow, converting the static image into a dynamic video sequence. This node is particularly adept at preserving the visual attributes of the character throughout the video, ensuring a seamless transformation from image to video. Additionally, the BatchImagesNode can be activated by selecting it and pressing Ctrl+B, enabling the processing of multiple images simultaneously for more complex projects.
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: Reference to Video" (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_i2v_api.json");
const asset = client.assets.fromFile("input.png");
wf.setInput("17", "image", asset); // LoadImage
const job = await client.run(wf);
await job.getOutputs("20")[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
