The Kling1.6: FLF2V workflow is designed to generate videos by precisely controlling the first and last frames, offering a unique approach to video synthesis. This workflow leverages the Kling model, specifically version 1.6, to ensure high-quality frame generation. The process begins with the LoadImage node, which allows users to input their desired starting and ending frames. These frames are then processed through the KlingStartEndFrameNode, a specialized node that interpolates the frames to create a smooth transition throughout the video. This node is crucial as it utilizes advanced algorithms to maintain consistency and coherence in the generated video.
The workflow concludes with the SaveVideo node, which compiles the interpolated frames into a seamless video file. Additionally, the MarkdownNote node provides users with contextual information and instructions, enhancing the user experience. This workflow is particularly useful for creators looking to generate videos with specific start and end visuals, making it ideal for applications such as promotional content, storytelling, and artistic video projects.
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 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");SDK 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
