This ComfyUI workflow streamlines high-quality image editing with the Grok Imagine Image Quality service. It connects three nodes in a simple path: LoadImage brings in your source, GrokImageEditNode sends your instructions (prompt) and the image to Grok’s API for enhancement and text cleanup, and SaveImage writes the improved result to disk. The workflow supports both image-to-image enhancement and prompt-driven generation, making it useful whether you’re fixing an existing picture or creating a clean, legible graphic from scratch.
Technically, GrokImageEditNode acts as the bridge to the Grok Imagine Image Quality endpoint, applying server-side upscaling, denoising, and advanced text rendering to improve clarity and readability while respecting your guidance. Your text prompt steers the edit (e.g., “sharpen details, clean signage text, preserve colors”), and any available controls in the node (such as strength, guidance, or resolution—depending on the node version) modulate how strongly the API alters the input. SaveImage then captures the returned image frames to your chosen output folder with your preferred filename prefix.
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 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");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.
FAQ
