This ComfyUI tutorial workflow, Nano Banana 2.1: Text to Image, is a minimal, fast text-to-image pipeline built around two nodes: ByteDanceSeedreamNodeV3 for image generation and SaveImageAdvanced for output. Your prompt flows directly into ByteDanceSeedreamNodeV3, which calls a remote API backend labeled "Nano Banana 2.1" to synthesize a single image without requiring any input files. Typical controls on this node include prompt/negative prompt, width/height, and seed for reproducibility (exact options depend on your installed node version and provider limits).
The generated image tensor is passed to SaveImageAdvanced, which handles file naming, format, metadata, and output directory. This makes it ideal for quick iterations on brand marketing posters, e-commerce product shots, or character series: type a clear prompt, optionally lock the seed for consistency, pick an aspect ratio, and hit Queue. The result is a clean, self-contained image saved to disk with metadata, ready for review or downstream editing.
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）。
