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/h8-52
This story in Turkish: Qwen-Image 2.1’in ağırlıkları açıldı
On the same topic
Anthropic releases Claude Haiku 5.5 at 90% lower prices
Claude Haiku 5.5, released Oct. 7, costs 90% less than Haiku 4.5 for prompts up to 100,000 tokens. It leads on benchmarks but uses more tokens per task.
OpenAI is rolling out GPT-6 to everyone in ChatGPT
OpenAI began rolling out GPT-6 to everyone in ChatGPT on October 7. Its new Intelligent UI builds answers from text, visuals and interactive elements.
The open model war between Europe, the US and China heats up
Mistral unveiled Large 4 on October 6. The same week, Ecosia dropped Mistral, Reflection AI launched Beam and DeepSeek was reported near a $12 billion round.