This ComfyUI workflow leverages the Flux.1 Redux model to generate images by transferring styles from reference images. At the core of this workflow are nodes like CLIPTextEncode and VAEDecode, which handle text encoding and image decoding respectively. The process begins with loading models using nodes like VAELoader and DualCLIPLoader, which prepare the necessary components for image generation. The workflow then utilizes the StyleModelApply node to apply the style of reference images onto the generated content, allowing for creative and visually appealing results.
What makes this workflow particularly useful is its ability to integrate multiple reference images, thanks to the chaining capability of the Apply Style Model nodes. This allows users to blend styles from different sources, creating unique and personalized outputs. Additionally, the workflow includes advanced sampling techniques with nodes like SamplerCustomAdvanced and KSamplerSelect, ensuring high-quality image generation. The inclusion of the FluxGuidance node provides further control over the image style, making this workflow ideal for artists and designers looking to experiment with style transfer in their projects.
API
Use this workflow from code
Every Comfy workflow is a JSON graph. The payload below is this workflow, exactly as ComfyUI runs it — fetch it from the URL, keep it in version control, or load it in ComfyUI and run it node by node.
Run it from TypeScript or Python with the Comfy SDK. The same code targets Comfy Cloud or a ComfyUI you host yourself — only the base URL changes.
// Install (beta)
npm i @comfyorg/sdk
// Run "Flux.1 Redux Model" (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("flux_redux_model_example_api.json");
const asset = client.assets.fromFile("input.png");
wf.setInput("40", "image", asset); // LoadImage
wf.setInput("6", "text", "A girl is walking in the natural wilderness."); // CLIPTextEncode
const job = await client.run(wf);
await job.getOutputs("9")[0].toFile("output.png"); // SaveImageThe SDK takes a workflow in API format: open this workflow in ComfyUI and use File → Export Workflow (API).
Comfy Cloud API access requires a plan with an API key.
FAQ
