This ComfyUI template builds a complete text-to-video pipeline around MiniMax H3 Max (Hailuo 03). At its core, MinimaxHailuo03TextToVideoNode turns your prompt from PrimitiveStringMultiline into a polished video, which is then written to disk by SaveVideo. SaveText also records the exact prompt that reached the generator so you can reproduce results later.
Two optional stages are wired behind ComfySwitchNode gates (visually marked in red) and controlled from the Feature Flags group. First, the Prompt Enhancer (Optional) can route your text through MinimaxHailuo03ContextIRNode before generation, producing a context IR object that the downstream node can use. Second, the Upscale Video to 2K (Optional) stage uses MinimaxHailuo03RegenerateNode to request a higher-resolution version of the same result. Important: the upscale stage only accepts a 768p source; set the base generator to 768p if you enable the Upscale to 2K boolean. This design lets you move quickly from idea to finished clip, then optionally refine fidelity and resolution without changing your base prompt.
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）。
