The Wan2.5: Text to Video workflow in ComfyUI is a sophisticated process designed to transform textual input into high-quality video content, optionally synchronized with audio. This workflow leverages the Wan2.5 and Wan models, which are renowned for their ability to generate smooth motion and superior visual quality in video outputs. At the core of this workflow is the WanTextToVideoApi node, which interprets text prompts and converts them into video sequences. Additionally, the workflow can incorporate audio through the LoadAudio and RecordAudio nodes, allowing for the creation of videos with synchronized soundtracks. This feature is particularly beneficial for content creators who wish to enhance their videos with custom audio tracks.
Technically, the workflow is structured to be user-friendly while providing advanced capabilities. Users can input audio files that are between 3 to 30 seconds long and under 15MB in size, which can be linked directly to the WanTextToVideoApi node for seamless integration. The SaveVideo node ensures that the final output is stored efficiently, while the MarkdownNote node provides a space for users to document their workflow settings and notes. This combination of nodes and models makes the Wan2.5: Text to Video workflow a powerful tool for producing engaging video content with ease.
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 "Wan2.5: 文生视频" (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_wan_text_to_video_api.json");
const job = await client.run(wf);
await job.getOutputs("7")[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
