←back to thread

Qwen VLo: From “Understanding” the World to “Depicting” It

(qwenlm.github.io)
221 points lnyan | 10 comments | 27 Jun 25 14:35 UTC | HN request time: 0.872s | source | bottom
Show context
rushingcreek ◴[27 Jun 25 14:51 UTC] No.44397235[source]▶
It doesn't seem to have open weights, which is unfortunate. One of Qwen's strengths historically has been their open-weights strategy, and it would have been great to have a true open-weights competitor to 4o's autoregressive image gen. There are so many interesting research directions that are only possible if we can get access to the weights.

If Qwen is concerned about recouping its development costs, I suggest looking at BFL's Flux Kontext Dev release from the other day as a model: let researchers and individuals get the weights for free and let startups pay for a reasonably-priced license for commercial use.

replies(4): >>44397843 #>>44397858 #>>44397893 #>>44398602 #
1. echelon ◴[27 Jun 25 16:07 UTC] No.44397893[source]▶
The era of open weights from China appears to be over for some reason. It's all of a sudden and seems to be coordinated.

Alibaba just shut off the Qwen releases

Tencent just shut off the Hunyuan releases

Bytedance just released Seedream, but it's closed

It's seems like it's over.

They're still clearly training on Western outputs, though.

I still suspect that the strategic thing to do would be to become 100% open and sell infra/service.

replies(6): >>44397943 #>>44398085 #>>44398090 #>>44399651 #>>44401386 #>>44403837 #
2. pxc ◴[27 Jun 25 16:10 UTC] No.44397943[source]▶
Why? And can we really say that already? Wasn't the Qwen3 release still very recent?
3. natrys ◴[27 Jun 25 16:25 UTC] No.44398085[source]▶
> Alibaba just shut off the Qwen releases

Alibaba from beginning had some series of models that are always closed-weights (*-max, *-plus, *-turbo etc. but also QvQ), It's not a new development, nor does it prevent their open models. And the VL models are opened after 2-3 months of GA in API.

> Tencent just shut off the Hunyuan releases

Literally released one today: https://huggingface.co/tencent/Hunyuan-A13B-Instruct

replies(1): >>44399326 #
4. logicchains ◴[27 Jun 25 16:25 UTC] No.44398090[source]▶
What do you mean Tencent just shut off the Hunyuan releases? There was another open weights release just today: https://huggingface.co/tencent/Hunyuan-A13B-Instruct . And the latest Qwen and DeepSeek open weight releases were under 2 months ago, there hasn't been enough time for them to finish a new version since then.
replies(1): >>44399335 #
5. echelon ◴[27 Jun 25 18:59 UTC] No.44399326[source]▶
Hunyuan Image 2.0, which is of Flux quality but has ~20 milliseconds of inference time, is being withheld.

Hunyuan 3D 2.5, which is an order of magnitude better than Hunyuan 3D 2.1, is also being withheld.

I suspect that now that they feel these models are superior to Western releases in several categories, they no longer have a need to release these weights.

replies(1): >>44399796 #
6. echelon ◴[27 Jun 25 19:00 UTC] No.44399335[source]▶
Hunyuan Image 2.0 and Hunyuan 3D 2.5 are not being released. They're being put into a closed source web-based offering.
7. jacooper ◴[27 Jun 25 19:40 UTC] No.44399651[source]▶
Deepseek R1 0528, the flagship Chinese model is open source. Qwen3 is open source. HIdream models are also open source
8. natrys ◴[27 Jun 25 20:02 UTC] No.44399796{3}[source]▶
> I suspect that now that they feel these models are superior to Western releases in several categories, they no longer have a need to release these weights.

Yes that I can totally believe. Standard corporation behaviour (Chinese or otherwise).

I do think DeepSeek would be an exception to this though. But they lack diversity in focus (not even multimodal yet).

9. amelius ◴[28 Jun 25 00:02 UTC] No.44401386[source]▶
era -> fluke
10. WiSaGaN ◴[28 Jun 25 11:13 UTC] No.44403837[source]▶
Deepseek and Alibaba just published their froniter models in open weights weeks ago. And they happen to be the leading open weights models in the world. What are you talking about?