What makes the Flux.2 Klein model suitable for real-time applications?

The Flux.2 Klein model is optimized for speed and efficiency, making it ideal for applications where latency is critical, such as live previews and interactive editing.

Can I use this workflow for batch processing multiple images?

While the workflow is optimized for real-time single image editing, you can adapt it for batch processing by iterating over multiple images using the 'LoadImage' node.

How do I adjust the image editing parameters?

You can adjust the parameters within the '7b34ab90-36f9-45ba-a665-71d418f0df18' node to customize the image edits according to your needs.

Is there documentation available for understanding subgraphs in this workflow?

Yes, you can refer to the [Subgraph docs](https://docs.comfy.org/interface/features/subgraph) for detailed information on how subgraphs function within the workflow.

Flux.2 [Klein] 4B Distilled: Image Edit

This ComfyUI workflow, titled 'Flux.2 [Klein] 4B Distilled: Image Edit', is designed to facilitate rapid image editing with a focus on interactive applications and real-time previews. Utilizing the Flux.2 Klein model, this workflow is optimized for latency-critical production environments where speed is paramount. The workflow employs several key nodes, including 'SaveImage' for output storage, 'LoadImage' for input handling, and a unique node identified as '7b34ab90-36f9-45ba-a665-71d418f0df18' for processing. Additionally, it features a 'MarkdownNote' node for documentation and guidance within the workflow itself.

Technically, the workflow leverages the power of the Flux.2 Klein model, known for its efficiency in processing and generating high-quality image edits quickly. The inclusion of the 'Multiple input example' workflow group allows users to toggle between different input configurations, enhancing flexibility and user control. This setup is particularly useful for users who need to make quick adjustments or iterations in a production setting, such as graphic designers or digital artists working under tight deadlines.

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.

image_flux2_klein_image_edit_4b_distilled.json

Fetching workflow JSON…

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.2 [Klein] 4B Distilled: Image Edit" (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_flux2_klein_image_edit_4b_distilled_api.json");

const asset = client.assets.fromFile("input.png");
wf.setInput("81", "image", asset);  // LoadImage

const job = await client.run(wf);
await job.getOutputs("9")[0].toFile("output.png");  // SaveImage

The 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.

SDK docs Get an API key

FAQ

Frequently Asked Questions