🚀 Introducing Qwen-Image-2.0 — our next-gen image generation model! 🎨 Your imagination, unleashed. ✨ Type a paragraph → get a pro slides ✨ Describe a scene → get photoreal 2K magic ✨ Add text → it just works (no more glitchy letters!) ✨ Key upgrades: ✅ Professional Show more
Qwen Image 2.0
Qwen Image 2.0 是阿里巴巴新一代统一图像生成与编辑模型,采用精简的 7B 参数架构。支持原生 2K 分辨率、业界领先的中英文双语文字渲染,以及最长 1000 token 的超长提示词,可生成专业信息图、照片级真实图像、海报等——全部由单一模型完成。
Qwen Image 2.0 Text-to-Image Gallery
Explore AI image creation with Qwen Image 2.0. Featuring native 2K resolution, industry-leading bilingual text rendering, and stunning photorealistic quality — from detailed infographics to macro photography.










Dance Portrait
A Black woman with waist-length loc'd hair mid-spin, locs fanning out with gold thread, cowrie shells, and blue beads under dramatic spotlight.
“A Black woman with waist-length loc'd hair caught mid-spin in a dance, her locs fanning out radially following centrifugal motion, some locs wrapped with gold thread, some with cowrie shells, some with blue beads. Individual locs are clearly separated and countable. She is wearing a flowing white dress also caught in the spin motion. Droplets of water flying off the loc tips against a dark background, lit by a single overhead spotlight creating a halo effect”
AI Image Editing with Qwen Image 2.0
Transform, restyle, and reimagine your images with Qwen Image 2.0's unified editing capabilities. From photographic style transfers to multi-image compositing and language translation — all powered by a single 7B model.
















Qwen Image 2.0 YouTube Videos
Watch community tutorials and reviews showcasing Qwen Image 2.0's capabilities
Qwen Image 2.0 Popular Reviews on X
See what people are saying about Qwen Image 2.0 on X (Twitter)
A quick update — we’ve fixed a Qwen-Image 2.0 bug in Qwen Chat that impacted: • Classical Chinese poem ordering in image generation • Character consistency during image editing ✅Patch is live now! chat.qwen.ai/?inputFeature=… Go test it out and drop us your feedback.
Qwen-Image 2.0 was released by @Alibaba_Qwen, marking a significant advancement in visual AI. Its most notable upgrade is the ability to render precise, legible text within images, including English and Chinese, enabling the creation of professional infographics, posters, and Show more
qwen has just announced a new image model, qwen-image-2.0, which merges qwen-image and qwen-edit into a single base. It ranked third in the generate ability test and second in the editing ability test. Not yet open source; currently available with API and chat webpage.
Qwen-Image is the new open weights image champion model, surpassing HiDream-I1-Dev with quality rivaling Imagen 3 and FLUX.1 Kontext [pro] in the Artificial Analysis Image Arena! Following the recent release of Wan2.2 A14B (the leading open weights video model), Alibaba has Show more
Qwen Image Edit 2509 is the new leading open weights image editing model, ranking #3 overall in the Artificial Analysis Image Editing Arena and introducing multi-image editing capabilities! The latest release from Alibaba Qwen trails only Gemini 2.5 Flash (Nano-Banana) and Show more
🇨🇳Alibaba’s Qwen-Image-2.0 Launches as Next-Gen Image Generation Model Alibaba’s Qianwen team has launched the next-generation image-generation foundation model Qwen-Image-2.0. The model’s API is now available for invited testing on Alibaba Cloud Bailian, and developers can also Show more
🚀 Qwen Image just got a big update on WaveSpeedAI! @Alibaba_Qwen ⚡ Generate ultra-accurate images in as fast as 5 seconds — just $0.02 per image and API ready! 🧠 Say goodbye to gibberish — Qwen Image nails text rendering like no other. Try it now 👉 wavespeed.ai/models/wavespe… Show more
Qwen-Image-2.0、驚異のフォトリアリズム能力で注目。 GTA画像生成例も公開され、プロンプト忠実度、編集、写実性で既存モデル凌駕の高性能。 開発チームは深層理解と高忠実度生成を単一7Bアーキテクチャで統合と明言。 現在公式サイトで利用可能、オープンソース化に期待集まる。 #QwenImage2 Show more
什么是 Qwen Image 2.0
阿里巴巴新一代统一图像生成与编辑AI,原生2K分辨率
Qwen Image 2.0 是一个 7B 参数的统一生成与编辑模型,以前代 1/3 的参数量实现了最先进的效果,具备业界领先的中英文双语文字渲染和 1000 token 超长提示词支持。
什么是 Qwen Image 2.0
阿里巴巴新一代统一图像生成与编辑AI,原生2K分辨率
Qwen Image 2.0 是一个 7B 参数的统一生成与编辑模型,以前代 1/3 的参数量实现了最先进的效果,具备业界领先的中英文双语文字渲染和 1000 token 超长提示词支持。
Qwen Image 2.0 功能特性
探索 Qwen Image 2.0 统一生成与编辑架构的强大能力
原生 2K 分辨率
原生生成 2048x2048 像素图像,无需上采样,在皮肤纹理、植被和建筑材质等细节上呈现壁纸级品质。
双语文字渲染
业界领先的中英文文字渲染能力,在海报、信息图、幻灯片和漫画中生成像素级精准的排版效果。
1000 Token 超长提示词
支持最长 1000 token 的超长提示词,可进行高度详细的布局指令描述,一句话生成复杂信息图和演示文稿。
统一生成与编辑
首个将文生图生成与图像编辑合并为单一架构的模型,无需使用额外的编辑模型。
3 倍参数效率
从 20B 精简至 7B 参数,同时在所有基准测试中提升质量,带来更快推理速度和更低计算成本。
多图参考编辑
支持最多 6 张参考图像用于编辑任务,实现复杂的多源合成、风格迁移和身份保持修改。
照片级真实品质
在 DPG-Bench (88.32) 和 AI Arena 排行榜中排名第一,在提示词遵循和视觉保真度上超越 FLUX 和 GPT-4V。
专业信息图生成
一句提示词即可创建数据丰富的信息图、演示幻灯片和营销材料,文字排版精准、布局结构清晰。
如何使用 Qwen Image 2.0 文生图
三步生成原生 2K 分辨率、文字渲染完美的精美图像
详细描述你想要创建的图像。Qwen Image 2.0 支持最长 1000 token 的提示词,可以包含具体的布局指令、文字内容和风格偏好。