This ComfyUI template demonstrates a high‑fidelity image editing pipeline that preserves the original subject, pose, lighting, and composition while making targeted changes. It’s built around a simple, reliable graph: LoadImage feeds a reference image into OpenAIGPTImageNodeV2 for natural‑language edits, and SaveImageAdvanced handles consistent output naming and metadata. The included sample asset (hairstyle_makeup_base_gpt_image25.png) lets you test the flow immediately.
Technically, OpenAIGPTImageNodeV2 calls an OpenAI GPT image model in image‑edit mode, using the source pixels as strong conditioning so that only requested elements (e.g., outfit, hairstyle, facial features, or camera angle) change. You guide the edit by writing a precise prompt that also states what must stay the same (for example: “Keep the same pose, lighting, background, and composition; only change the hairstyle to a short bob”). This makes the workflow excellent for sequential frames and subject‑consistent variations. SaveImageAdvanced then writes the results with versioned filenames so iterations are easy to track.
API
코드에서 이 워크플로우 사용하기
모든 Comfy 워크플로우는 JSON 그래프입니다. 아래 페이로드는 이 워크플로우 그 자체로, ComfyUI에서 실행되는 것과 동일합니다 — URL에서 가져오거나, 버전 관리에 보관하거나, ComfyUI에서 불러와 노드별로 실행할 수 있습니다.
Comfy SDK로 TypeScript 또는 Python에서 실행하세요. 동일한 코드는 Comfy Cloud 또는 직접 호스팅하는 ComfyUI 모두에 적용됩니다 — 기본 URL만 다릅니다.
// 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");SDK는 API 형식의 워크플로우를 사용합니다: 이 워크플로우를 ComfyUI에서 열고 파일 → 워크플로우 내보내기(API)를 사용하세요.
