‹ BackHN Continuity

Thread

Qwen Image 2.1

740 points · 199 comments · jmillikin

  1. vunderba · · focus · HN ↗
    So thoughts

    Positives

    • It's a heck of a lot smaller than Qwen-Image 1 (20b parameters) at only 7b, making it one of the smaller open-weight models available (Z-Image Turbo is one of the few that is smaller at 6b) when compared to Ideogram, Krea2, Flux2, etc.

    • It supports native transparency (Qwen's team, as far as I know, is the only one attempting to tackle this). Even though it's relatively trivial to set up background removal postprocessors, it's also neat to see it natively supported.

    • It's fast using QwenImage2.1 convrot, a 1MP image took around ~5 seconds on an RTX4090.

    Negatives

    • The license (assuming you respect it) is far more restrictive. The original Qwen Image 1 was released under the standard Apache license; this one explicitly forbids commercial usage without obtaining a separate license. On the other hand, a lot of us didn't expect the Qwen team to ever release "weights-available" ever again.

    Qwen-Image 1.0, released about a year ago, only scored 4/15 on my GenAI Showdown Benchmarks. Since that time, they've been upstaged by Krea 2 (6/15) and Ideogram4 (8/15). I'll post the new results once I have some more time to run them.

    <a href="https:&#x2F;&#x2F;genai-showdown.specr.net" rel="nofollow">https:&#x2F;&#x2F;genai-showdown.specr.net

    1. alightsoul · · focus · HN ↗
      They&#x27;re trying to cash in but this is just sad
      1. thenthenthen · · focus · HN ↗
        Within a few days this seems a total pivot from Xiaomi’s op RL dashboard and the praise of Chinese open model? What is the sentiment now?
        1. Foobar8568 · · focus · HN ↗
          Qwen can&#x27;t train anymore with openai reasoning tokens? I kid I kid.
Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.