Qwen Image Edit

by Alibaba

Image editing model by Alibaba's Qwen team, version 2511. 20B MMDiT with native multi-image editing (up to 3 reference images in one edit), improved facial identity preservation and instruction following. Shares text encoder and VAE with Qwen Image.

ImageApache 2.0Released Dec 202520B parameters

Hugging Face repo ↗Alibaba ↗

Drag or click to move along the pipeline

full qualitylightest

Lighter tiers fit smaller GPUs and lose some detail. Start with the heaviest one that loads.

The model

Qwen Image Edit

BF1653.7 GB

Three pieces, three separate downloads.

Diffusion modelGoes in diffusion_models/

Generates the image

38.1 GB↓↗

Text encoderGoes in text_encoders/

Turns your prompt into guidance

15.4 GB↓↗

VAEGoes in vae/

Decodes the result into pixels

0.2 GB↓↗

LoRAs (optional)Goes in loras/

0.8 GB↓↗

SamplerKSampler

Copy these values into your KSampler.

Steps20

CFG4

Samplereuler

Schedulersimple

Native res.1024x1024 (native)

Shift3.1

Usage notes

GGUF is the lightest way to run this model.

Apache 2.0. Check the official repo for usage terms.

Click a file name to copy it.