The Kling 3.0: Video Generation workflow is designed to transform text or image prompts into captivating 15-second video sequences. This workflow leverages the Kling 3.0 model, renowned for its ability to create multi-shot compositions and complex camera movements while maintaining subject consistency throughout the video. The workflow integrates several key nodes, including LoadImage for initial prompt input, KlingVideoNode for generating the video content, and SaveVideo for exporting the final product. By utilizing these nodes, users can create dynamic videos that are not only visually appealing but also coherent in their narrative structure. This makes the workflow particularly useful for content creators looking to produce engaging video content with minimal input.
API
從程式碼使用此工作流
每個 Comfy 工作流都是一個 JSON 圖。下方的 payload 就是此工作流，與 ComfyUI 執行時完全相同 — 你可以從此 URL 取得、放入版本控制，或在 ComfyUI 載入並逐節點執行。
使用 Comfy SDK 以 TypeScript 或 Python 執行。相同程式碼可用於 Comfy Cloud 或你自架的 ComfyUI — 只需更改 base URL。
// Install (beta)
npm i @comfyorg/sdk
// Run "Kling 3.0：影片產生" (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_v3_video_api.json");
const asset = client.assets.fromFile("input.png");
wf.setInput("1", "image", asset); // LoadImage
const job = await client.run(wf);
await job.getOutputs("2")[0].toFile("output.png"); // SaveVideoSDK 需使用 API 格式的工作流：請在 ComfyUI 開啟此工作流，並使用 檔案 → 匯出工作流（API）。
常見問題
