This advanced ComfyUI workflow is designed to create multi-shot user-generated content (UGC) videos featuring your character and product. It leverages the power of the Kling 3.0 and Nano Banana 2 models to seamlessly integrate both elements into a cohesive video narrative. The workflow begins with the 'LoadImage' nodes for uploading your character and product images, followed by the 'GeminiNanoBanana2' node, which performs semantic editing to blend these images effectively. The 'BatchImagesNode' and 'KlingOmniProImageToVideoNode' are then used to generate a series of storyboard shots, which are compiled into a video using the 'SaveVideo' node.
What makes this workflow particularly useful is its ability to produce engaging UGC videos that can be used for marketing or storytelling purposes. By selecting the number of shots and writing specific prompts for each, users can customize the video to match their creative vision. The Kling 3.0 model ensures high-quality video output, while the Nano Banana 2 model provides flexibility in aspect ratio selection, making it adaptable to various platforms and audiences.
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 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");The 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.
الأسئلة الشائعة
