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
通过代码使用此工作流
每个 Comfy 工作流都是一个 JSON 图。下面的内容就是此工作流的完整数据，ComfyUI 运行时也是如此——你可以从该 URL 获取、放入版本控制，或在 ComfyUI 中加载并逐节点运行。
使用 Comfy SDK 从 TypeScript 或 Python 运行。相同代码可用于 Comfy Cloud 或你自托管的 ComfyUI——只需更改基础 URL。
// Install (beta)
npm i @comfyorg/sdk
// Run "产品场景转换" (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"); // SaveVideoSDK 需要 API 格式的工作流：在 ComfyUI 中打开此工作流，使用 文件 → 导出工作流（API）。
常见问题
