The LTX-2.3: Text to Video workflow in ComfyUI is designed to transform a text prompt into a dynamic video, with the option to use an image as a reference. This workflow leverages the LTX-2.3 model, developed by Lightricks, which is optimized for generating high-quality videos with enhanced motion, audio, and detail. The workflow is particularly effective for creating videos in both portrait and landscape formats, making it versatile for various applications.
Technically, the workflow integrates several key nodes, including the SaveVideo node for outputting the final video, and the LoadImage node for incorporating reference images. The MarkdownNote node is used to provide inline documentation and guidance within the workflow. The core of the process involves using the b94257db-cdc1-45d3-8913-ca61e782d9c1 node, which is responsible for interpreting the text prompt and generating the corresponding video content. This workflow is beneficial for users looking to quickly produce visually compelling videos from textual descriptions, with the added ability to refine the output using reference images.
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 "LTX-2.3: 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("video_ltx2_3_t2v_api.json");
const job = await client.run(wf);
await job.getOutputs("75")[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
