The Product Scene Transformation workflow is designed to enhance product videos by dynamically transforming scenes using advanced AI models. This workflow utilizes the power of the Nano Banana Pro and Wan VACE 2.1 models to generate seamless transitions between different product scenes. It employs a series of nodes, including the KlingImage2VideoNode, which is responsible for converting static product images into dynamic video sequences. The workflow is structured into three main groups: creating the initial product scene animation, rendering the final video, and creating reference images for consistency. By leveraging the comfyui-depthanythingv2 and comfyui-kjnodes, this workflow ensures that depth and style transfer are effectively applied to enhance the visual appeal of product videos.
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 "Product Scene Transformation" (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("templates_product_scene_transformation_api.json");
const asset = client.assets.fromFile("input.png");
wf.setInput("108", "image", asset); // LoadImage
const job = await client.run(wf);
await job.getOutputs("126")[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
