Qwen-Image-Edit

Name: Qwen-Image-Edit-2509
Availability: InStock
Author: 阿里巴巴

多模态大模型

Qwen-Image-Edit-2509

Release date: 2025-09-22更新于: 2025-09-23 08:38:39717

Live demo GitHub Hugging Face Compare

Parameters

300.0亿

Context length

128K

Chinese support

Supported

Reasoning ability

Qwen-Image-Edit-2509 is an AI model published by 阿里巴巴, released on 2025-09-22, for 多模态大模型, with 300.0B parameters, and 128K tokens context length, requiring about 60GB storage, under the Apache 2.0 license.

Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology

Qwen-Image-Edit

Model basics

Reasoning traces

Supported

Thinking modes

Thinking modes not supported

Context length

128K tokens

Max output length

4096 tokens

Model type

多模态大模型

Release date

2025-09-22

Model file size

60GB

MoE architecture

Yes

Total params / Active params

300.0B / 30B

Knowledge cutoff

No data

Qwen-Image-Edit

Open source & experience

Code license

Apache 2.0

Weights license

Apache 2.0- 免费商用授权

GitHub repo

https://github.com/QwenLM/Qwen-Image

Hugging Face

https://huggingface.co/Qwen/Qwen-Image-Edit-2509

Live demo

https://huggingface.co/Qwen/Qwen-Image-Edit-2509

Qwen-Image-Edit

Official resources

Paper

Qwen-Image-Edit-2509: Multi-Image Support，Improved Consistency

DataLearnerAI blog

No blog post yet

Qwen-Image-Edit

API details

API speed

3/5

No public API pricing yet.

Qwen-Image-Edit

Benchmark Results

No benchmark data to show.

Qwen-Image-Edit

Publisher

阿里巴巴

View publisher details

Qwen-Image-Edit-2509

Model Overview

DataLearner 官方微信

欢迎关注 DataLearner 官方微信，获得最新 AI 技术推送