This ComfyUI workflow transforms a single still image into a short, cinematic video using the PixverseV6ImageToVideoNode. The graph is intentionally simple and production-focused: LoadImage brings in your source asset, PixverseV6ImageToVideoNode sends it to the PixVerse V6 image-to-video model via API for motion synthesis, and SaveVideo writes the returned clip to disk. The node exposes controls for duration (up to ~15 seconds), resolution selection from 360p through 1080p, and common aspect ratios, so you can quickly target platforms like TikTok, Instagram, or YouTube without additional resizing steps.
Technically, the PixverseV6ImageToVideoNode handles the heavy lifting off-device through the PixVerse service, so you don’t need a local GPU. You can guide motion and subject behavior with text direction in the node (for example, describing camera moves or the action you want). If your build of the node includes multi-shot/storyboard fields, you can specify timed beats or per-shot prompts for cohesive narrative flow; if not, stick with a single continuous shot. A MarkdownNote is included on-canvas to provide quick reminders. Finally, SaveVideo packages the generated clip to your ComfyUI output folder for immediate review and sharing.
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）。
