The Kling O3: FLF2V workflow is designed to generate videos with precise semantic control and enhanced narrative coherence. This workflow leverages the Kling O3 model, which is known for its ability to maintain consistency across frames while allowing for detailed control over the video’s storyline. By using nodes such as SaveVideo, LoadImage, and BatchImagesNode, users can upload reference images to guide the video's context or specify start and end frames for a structured narrative. The KlingOmniProFirstLastFrameNode is particularly crucial as it facilitates the seamless transition between frames, ensuring that the narrative flow remains uninterrupted. This makes the workflow especially useful for creating longer-duration videos where maintaining thematic consistency is essential.
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 "Kling O3：首尾帧视频" (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_o3_flf2v_api.json");
const asset = client.assets.fromFile("input.png");
wf.setInput("36", "image", asset); // LoadImage
const job = await client.run(wf);
await job.getOutputs("14")[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
