Qwen/Qwen-Image-2.1 — new model trending #30 on Hugging Face
Alibaba's Qwen open-sourced Qwen-Image-2.1, a 7B-parameter unified text-to-image generation and editing model with native RGBA transparency.
Alibaba's Qwen team open-sourced Qwen-Image-2.1, a unified text-to-image generation and image editing model with a 7B-parameter visual generation component built from 32 single-stream DiT layers. It natively generates and edits transparent RGBA images, supports up to 10 reference images, and enables local edits via circles, annotations, or masks with identity preservation for people and products. Efficiency comes from mixed-granularity attention and prefix KV cache reuse, with improved typography, portrait lighting, and textures. Weights are available on Hugging Face and ModelScope under the Qwen Research License Agreement.
- 7B-parameter visual generation component using 32 single-stream DiT layers.
- Generates and edits transparent RGBA images natively from text prompts.
- Supports up to 10 reference images and localized edits via masks or circles.
- Mixed-granularity attention and prefix KV cache reuse cut inference cost.
- Licensed under the Qwen Research License Agreement.
- Vendors
- AlibabaQwenHugging Face
- Products
- Qwen-Image-2.1
- Organizations
- Alibaba
- AI models
- Qwen-Image-2.1
From the original article
2 min read at huggingface.co<img src="https://qianwen-res. oss-cn-beijing. aliyuncs.
By Qwen · huggingface.co
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.