Models · Image and video · Alibaba
Qwen-Image 2.1’s weights were opened
Alibaba’s Qwen team released the model on September 20 simultaneously on Hugging Face, ModelScope and GitHub. One model both generates images from text and edits them, with 7 billion parameters in the generation component. It can output transparent PNGs straight from a prompt instead of faking them with a background-removal pass. ComfyUI, Diffusers, vLLM-Omni and SGLang support it from day zero. The important detail is the license: the Qwen Research License permits non-commercial use only, and commercial use requires a separate license by email.
Sources
- Qwen (GitHub), “QwenLM/Qwen-Image-2.1”, official GitHub repository and README, (github.com)
- Hugging Face (Qwen), “Qwen/Qwen-Image-2.1”, model card (huggingface.co)
- Qwen, Qwen blog announcement (qwen.ai)
About this story
This story was posted on Instagram by @jarrus.tech on Sept. 27, 2026.
Spotted an error in this story? [email protected] · Instagram
Short link: thejarrus.com/en/qwen-image-2-1
This story in Turkish: Qwen-Image 2.1’in ağırlıkları açıldı
On the same topic
OpenAI’s image model posts a near-perfect score on text-dense images
On UltraText Bench, a dense-text test led by Westlake University, OpenAI’s GPT Image 2 ranked first of 24 configurations with 99.35 out of 100.
AWS adds Chinese lab Z.ai’s GLM 5.3 model to Amazon Bedrock
AWS added GLM 5.3, a 753-billion-parameter model from Beijing-based Z.ai (formerly Zhipu AI), to Amazon Bedrock for eligible enterprise customers on October 5.
Higgsfield launches Ads Studio, turning a website into ad images for about 20 cents each
Higgsfield’s Ads Studio, announced October 1, builds a brand kit from a website and makes up to 20 static ads per product at about $0.20 each.