This MiniMax H3 Max Turbo image-to-video workflow turns a single still image into motion in seconds and saves two distinct clips per run. The core video generation happens in parallel through two MiniMax nodes: MinimaxHailuo03FirstLastFrameNode and MinimaxHailuo03ContextIRNode. Both consume the same start image from LoadImage and the same text prompt, then SaveVideo writes each result to disk. A ComfySwitchNode sits between your prompt and the generators, routing either your original text from PrimitiveStringMultiline or an auto-improved version from MinimaxHailuo03RegenerateNode when the Prompt Enhancer is enabled. For traceability, SaveText captures prompt metadata so you can reproduce strong results later.
Two optional stages are exposed via the Feature Flags group (PrimitiveBoolean). First, you can enable the Prompt Enhancer to have MinimaxHailuo03RegenerateNode refine your instruction before it is passed to both video generators. Second, you can enable 2K upscaling for higher-resolution deliverables. Important: the upscale stage only accepts 768p source video, so set the MiniMax generation resolution to 768p when you plan to upscale. The template also includes MarkdownNote guidance on-canvas and sensible defaults to get you from a single frame to dual video outputs fast, making it ideal for animating stills, storyboards, and quick VFX look-dev.
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）。
