Qwen Image Edit 2511 (Int8)

by Comfy OrgWorkflowMake visuals

Edits a photo from a plain instruction, built to keep the person's identity consistent

About Qwen Image Edit 2511 (Int8)

An official ComfyUI workflow template for editing a photo from a plain instruction, using Alibaba's Qwen-Image-Edit-2511 model in a smaller int8 version. Load one picture, describe the change and get one edited image.

For Creators and illustratorsDesigners making variationsOnline sellers

Made by Comfy Org

Comfy Org is a San Francisco company that develops ComfyUI, an open-source tool for visual AI. This template comes from its official workflow_templates repository.

Stars: ★ 1.4k
License: MIT
Cost: Free
Level: Intermediate
Platform: comfyui

Examples

From the project's own repository · 2 images, swipe or use the arrows.

Example output of the template: a portrait of a woman with pink lilies, restyled as a pop-art poster — Image: Comfy Org (MIT). Original file

The template's sample input: a woman with curly hair and pink lilies against a blue wall — Image: Comfy Org (MIT). Original file

Overview

This is an official ComfyUI workflow template for Qwen-Image-Edit-2511 from Alibaba's Qwen team, using a smaller int8 version of the model. You load one picture and describe the change, for example turn it into a pop-art poster, and it returns one edited image. The model is built to keep a person's identity steady across edits and can also change materials on objects. It suits creators, designers and online sellers who edit pictures on their own computer.

The model is built to keep faces and characters consistent while it restyles or changes a picture, and its files are under the Apache 2.0 license.

Try these first

Start with the first one: it is a small task you can check easily.

Load a photo you own and ask: "Convert this image to pop art poster style." Compare the result with the original.First try · about 29 GB download
Change the sofa's leather to soft grey fabric and keep everything else the same.
Put the person in a navy blazer and keep the face, hair and background unchanged.

Example prompts written by Agent Flows Hub.

How it works

From the creator's documentation.

Step	What happens	Data goes to
1 · Model files	ComfyUI lists the int8 edit model, text encoder, VAE and a speed-up LoRA, about 29 GB	Your computer
2 · Picture	You load one image	Your computer
3 · Instruction	You describe the change in plain words	Your computer
4 · Edit	Qwen-Image-Edit-2511 makes the change on your graphics card, built to keep people's look consistent	Your computer
5 · Save	ComfyUI saves the edited picture	Your computer

Good to know

Edit one input image with a written instruction using the official Qwen-Image-Edit-2511 int8 ComfyUI graph. The template loads the model, encodes your picture and instruction, and saves the edited image.

Limits

The listed model files take about 29 GB of disk space, and graphics memory needs depend on your card. Use the files and ComfyUI version the template names.
An edit can change details you did not ask about. Compare faces, text and product features with the original before using the result.

Notes by Agent Flows Hub (original project name: image_qwen_image_edit_2511_int8 (ComfyUI template)), written from the creator's documentation, not from running it ourselves. Qwen-Image-Edit-2511 in ComfyUI: official tutorial · Qwen Image Edit 2511 Int8: pinned ComfyUI template

Stuck setting it up?

Tell us what happened. We take a look first; if it needs paid work, you get an estimate before anything starts.

Get help

How to start

Open comfyuiYour own server or the platform's cloud.
Import the templateDownload it from the creator's page and import it or follow the official guide. An AI agent can walk you through it with the install request.
Run it once with test dataLoad a photo you own, ask for one style change and compare the edited picture with the original, side by side.

Steps follow the creator's instructions. The request tells your agent to read them first and wait for your OK.

Before you start

comfyui, on your own server or the platform's cloud.
ComfyUI installed: Comfy Desktop (Windows, macOS, Linux), Portable or a manual install
A dedicated graphics card; ComfyUI recommends NVIDIA or AMD
About 29 GB of free disk space for the model files
Free. Nothing to pay.

Details

Made by: Comfy Org
License: MIT Terms
Runs on: Your computer

View source Official docs Report a problem

For AI agents

This page as a Markdown install brief:

/en/library/comfyui-qwen-image-edit-2511/install.md

Other workflows

Remove Background (BiRefNet) Removes the background from a photo and gives you a transparent cut-out and a mask
SeedVR2 Video Upscale Turns a grainy, low-resolution video clip into a cleaner, higher-resolution one
Thread Writer (Langflow) Turns a project brief into a ready-to-post thread or single post for X (Twitter)
Wan Animate 2 Motion Transfer Makes a character from one picture copy the moves of a person in a video
Web Search Summarizer (Dify) Searches the web for your question and returns a table that summarises each page
Writing Assistant (Dify) Writes a first draft of a social post from your brief, then waits for your approval

See all 25 workflows

GitHub