• Home
  • Technology
  • Gaming
  • Entertainment
  • World & Business
  • Science
  • Sports
  • AI
HomeTechnologyGamingEntertainmentWorld & BusinessScienceSportsAI
Technology

Qwen releases open weights for Qwen-Image-2.1 image model

Qwen says the 7-billion-parameter model combines image generation and editing, with support for up to 10 reference images and native transparency.

Ihtesham AliIA
Ajit SahooAS
2 Sources, 20d ago, first seen 20d ago

TLDR

Qwen has released open weights for Qwen-Image-2.1. The team says the model supports precise local edits and can generate and edit transparent image layers, including text within them. Qwen also claims it preserves portrait and product details during editing, and highlights uses including panoramas, infographics and virtual try-ons.

Combined views

4K

2 Sources, first seen 20d ago

31 likes7 comments16 saves15 reposts

Combined views

4K

2 Sources, first seen 20d ago

31 likes7 comments16 saves15 reposts

Sentiment

Positive——Negative

Summary

Not enough discussion yet.

No sentiment analysis available yet.

Featured Source

Sentiment

Positive——Negative

Summary

Not enough discussion yet.

No sentiment analysis available yet.

Related

Alibaba stock reportedly fell after earnings as profit dropped 76% and capex rose 75%

Tech in Asia reported that Alibaba’s profit fell 76% while capex rose 75%, and said the stock dropped after earnings as investors may be missing its broader chips, cloud, AI and apps push.

China weighs allowing Nvidia RTX Pro 5500 purchases by Alibaba and ByteDance

The Information reports that officials asked companies how many chips they want and how they plan to use them, but approval terms remain unclear.

Alibaba unveils Zhenwu V900 AI chip, targets more than 20GW of global data center capacity by 2032

A post says the V900 is designed to train and run AI models, with mass production and commercial release expected in Q1 2027. It describes claimed performance roughly 3x higher than the chip’s predecessor.

2 Sources

Ihtesham Ali@ihteshamaliokay you NEED to see this... Qwen just dropped an open-source AI that can generate AND edit 2K images but that's not even the crazy part... You can give it up to 10 reference images and bring them together in one scene. Qwen-Image-2.1 can also: 1. Turn separate portraits into a group photo. 2. Combine clothes, shoes, and accessories into one outfit. 3. Edit specific areas you circle. 4. Generate transparent backgrounds. 5. Create posters with detailed text. Imagine taking your product photo, a model, and an outfit, then describing the shot you want. The weights are available now. ComfyUI already supports it. https://github.com/qwenlm/qwen-image-2.120d
Ajit Sahoo@Ajit9797Every few weeks a new 'most balanced, most cost-effective' image model drops and gets forgotten in a month. Alibaba just dropped open weights for a top-tier image model while the big US labs keep theirs locked behind an API. Open source in AI keeps quietly winning on cost, even when nobody's watching20d
    • Home
    • Technology
    • Gaming
    • Entertainment
    • World & Business
    • Science
    • Sports
    • AI
    Alibaba GroupQwen-Image-2.1

    2 Sources

    Ihtesham Ali@ihteshamaliokay you NEED to see this... Qwen just dropped an open-source AI that can generate AND edit 2K images but that's not even the crazy part... You can give it up to 10 reference images and bring them together in one scene. Qwen-Image-2.1 can also: 1. Turn separate portraits into a group photo. 2. Combine clothes, shoes, and accessories into one outfit. 3. Edit specific areas you circle. 4. Generate transparent backgrounds. 5. Create posters with detailed text. Imagine taking your product photo, a model, and an outfit, then describing the shot you want. The weights are available now. ComfyUI already supports it. https://github.com/qwenlm/qwen-image-2.120d
    Ajit Sahoo@Ajit9797Every few weeks a new 'most balanced, most cost-effective' image model drops and gets forgotten in a month. Alibaba just dropped open weights for a top-tier image model while the big US labs keep theirs locked behind an API. Open source in AI keeps quietly winning on cost, even when nobody's watching20d
    Today's Rank

    —

    Not ranked yet

    Today's Rank

    —

    Not ranked yet