The Image Relight workflow is designed to enhance and modify the lighting of images using advanced AI techniques. At its core, this workflow leverages the Qwen-Image-Edit model, which is known for its ability to perform intricate image editing tasks with support for LoRA (Low-Rank Adaptation) to fine-tune the model's performance on specific tasks. The workflow begins by loading an image through the LoadImage node, which serves as the input for the relighting process. The Qwen-Image-Edit model then processes the image, adjusting the lighting to achieve the desired effect. This is particularly useful for photographers and digital artists looking to enhance the mood or highlight specific elements within an image. The workflow concludes with the SaveImage node, which outputs the newly relit image, ready for use in various applications.
Technically, the workflow is structured to allow users to input specific lighting parameters through a combination of MarkdownNote and StringConcatenate nodes, providing a user-friendly interface for customizing the relighting process. The PrimitiveStringMultiline node is utilized to handle complex string inputs, ensuring that the workflow can accommodate detailed instructions and settings. This makes the Image Relight workflow not only powerful but also highly adaptable to different user needs, making it a valuable tool for anyone looking to improve their image editing capabilities.
API
通过代码使用此工作流
每个 Comfy 工作流都是一个 JSON 图。下面的内容就是此工作流的完整数据，ComfyUI 运行时也是如此——你可以从该 URL 获取、放入版本控制，或在 ComfyUI 中加载并逐节点运行。
使用 Comfy SDK 从 TypeScript 或 Python 运行。相同代码可用于 Comfy Cloud 或你自托管的 ComfyUI——只需更改基础 URL。
// Install (beta)
npm i @comfyorg/sdk
// Run "照片重打光" (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("image_qwen_image_edit_2509_relight_api.json");
const asset = client.assets.fromFile("input.png");
wf.setInput("11", "image", asset); // LoadImage
const job = await client.run(wf);
await job.getOutputs("12")[0].toFile("output.png"); // SaveImageSDK 需要 API 格式的工作流：在 ComfyUI 中打开此工作流，使用 文件 → 导出工作流（API）。
常见问题
