Qwen-Image-2.1-PE-I2I

Model release Hugging Face 模型 · Qwen Source language: Chinese

官方机构模型仓库创建于 2026-09-20。仓库创建时间不等于正式发布日期。任务类型:未提供

Full text

🤖 ModelScope      🤗 HuggingFace      📑 Blog      🖥️ Demo      🫨 Discord

Introduction

We are excited to open-source Qwen-Image-2.1, a unified text-to-image generation and image editing model in the Qwen family. With just 7B parameters in its visual generation component (32 Single-Stream DiT layers), Qwen-Image-2.1 balances generation quality, inference efficiency, and versatility.

Four key improvements define this release:

Compact and Efficient — A lightweight architecture with mixed-granularity attention and prefix KV cache reuse delivers strong image quality at low computational cost. Native Transparency, Unified Creation and Editing — Generate regular or transparent (RGBA) images from text, edit transparent layers, and extract subjects from photographs—all in one model. Versatile Editing — Support up to 10 reference images, specify local edits via circles, painted annotations, or separate masks, and preserve identity for people and products. Realistic Textures and Refined Aesthetics — Improved typography, portrait lighting, and fine details for more visually compelling results.

Qwen-Image-2.1-PE-I2I

Image editing prompt rewriting model for Qwen-Image-2.1. A fine-tuned Qwen3.5-VL 9B that takes a vague editing instruction plus input image(s) and produces a precise, actionable prompt suitable for downstream image editing.

For more details, see the GitHub repo and Blog.

Quick Start

Installation

Usage with Transformers

Multi-Image Editing

The model supports multiple input images — referred to as , , etc.:

Integration with Diffusers

Output Format

The model outputs a JSON object after a reasoning block:

rewritten_prompt — the expanded prompt to pass to the image editing model wh_ratio — aspect ratio chosen by the model (e.g. "16:9"), when the task creates a new composition ratio_follow — inherit aspect ratio from an input image (e.g. " "), when editing in-place

wh_ratio and ratio_follow are mutually exclusive — exactly one carries a value.

License

This model is licensed under the Qwen Research License Agreement.

Sources

← Back to the daily brief