GPT Image 2.5 Flare: Text to Image is a lean ComfyUI template for rapid ideation and fast visual drafts. It centers on OpenAIGPTImageNodeV2 for generation and optional editing, then hands results to SaveImage for clean, consistent exports. With only two nodes to manage, you can move quickly from prompt to preview, making it ideal for mood boards, poster comps, character studies, and quick scene mockups.
Technically, OpenAIGPTImageNodeV2 sends your prompt (and, if provided, a source image and mask) to an OpenAI image model you select in the node’s model field (for example, gpt-image-1). The node returns generated images directly into ComfyUI for preview, and SaveImage writes them to disk with your chosen filename prefix and subfolder. The “Flare” preset emphasizes low latency: keep sizes modest, use standard quality, and generate a small batch to iterate quickly, then scale up resolution or quality once the concept is locked.
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）。
