This ComfyUI workflow, titled 'HiDream E1.1 Image Editing', offers a comparative analysis between two image editing models: HiDream E1.1 and HiDream-E1-Full. The primary focus of this comparison is to evaluate the image quality and editing accuracy of both models. HiDream E1.1 is touted for its superior image quality and precision in editing tasks, which is crucial for users who require high fidelity in image modifications. The methodology involves using various nodes such as CLIPTextEncode, VAEDecode, and KSamplerSelect to process and edit images based on user prompts. Key differences include the handling of image details and the ability to maintain the integrity of unedited portions of the image, which is where HiDream E1.1 excels compared to its predecessor.
The workflow is structured into several steps, starting with model loading and image uploading, followed by prompt-based editing using the InstructPixToPixConditioning node. The comparison is particularly insightful for users who need to make informed decisions about which model to use for specific image editing tasks. By understanding the strengths of HiDream E1.1, users can leverage its capabilities for tasks that demand high precision and quality, while also considering the trade-offs in processing time and resource usage.
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 "HiDream E1.1 Image Editing" (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("hidream_e1_1_api.json");
const asset = client.assets.fromFile("input.png");
wf.setInput("13", "image", asset); // LoadImage
wf.setInput("6", "text", "your prompt here"); // 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
