The 'Flux.1 Krea Dev' workflow leverages a fine-tuned FLUX model to achieve high levels of photorealism in image generation. This workflow is designed for users who seek to create stunningly realistic images from textual descriptions. It employs a combination of nodes, including SaveImage and MarkdownNote, which facilitate the process of generating and saving high-quality images. The core of this workflow is the Flux.1 Krea Dev model, known for its ability to push the boundaries of photorealism. By utilizing this model, users can expect images that are not only visually appealing but also highly detailed and true to life.
Technically, the workflow operates by taking a text input and processing it through the Flux.1 Krea Dev model. This model interprets the textual data and translates it into a photorealistic image. The SaveImage node then ensures that the output is stored efficiently, while the MarkdownNote node can be used to annotate the process or results. This workflow is particularly useful for artists, designers, and content creators who need to produce realistic images quickly and efficiently. Its ease of use and the quality of output make it a valuable tool in any creative toolkit.
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 "Flux.1 Krea Dev" (TypeScript)
import { Comfy } from "@comfyorg/sdk";
const client = new Comfy({ apiKey: "comfyui-..." });
// This workflow, exported in API format (see note below)
const wf = await client.workflows.fromFile("flux1_krea_dev_api.json");
const job = await client.run(wf);
await job.getOutputs("9")[0].toFile("output.png"); // SaveImageSDK 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）。
常見問題
