The Kling O3: Image Generation workflow is designed to create new images by leveraging a set of up to 10 reference images. At its core, this workflow uses the Kling O3 model, a sophisticated image synthesis model known for its ability to blend multiple visual inputs into a cohesive new image. The process begins by loading your reference images using the LoadImage node, which allows the workflow to access and process up to 10 images simultaneously. These images are then handled by the BatchImagesNode, which organizes them for efficient processing and synthesis. The KlingOmniProImageNode is where the magic happens; it takes the batched images and synthesizes a new image that encapsulates the essence of the input images. Finally, the SaveImage node ensures that the generated image is saved to your desired location, making it easy to access and use in your projects.
This workflow is particularly useful for artists and designers who want to create unique images that draw inspiration from multiple sources. By using the Kling O3 model, users can achieve high-quality results that reflect the nuances of the input images. The workflow's ability to handle multiple inputs and produce a single, unified output makes it a powerful tool for creative projects that require a blend of different visual styles or themes.
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: Image Genertaion" (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_image_api.json");
const asset = client.assets.fromFile("input.png");
wf.setInput("31", "image", asset); // LoadImage
const job = await client.run(wf);
await job.getOutputs("29")[0].toFile("output.png"); // SaveImageThe 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
