Hacker News

Well, the results are in, at least for text-to-image (the editing bench will come later).

Qwen-Image 2.1 is definitely a pretty big leap over the last open-weight version, Qwen-Image 1.0, released back in August of last year and managed to score 7 out of 15 as opposed to its predecessor which scored 4 out of 15.

Even though it's significantly smaller, 7b vs 20b, it's multimodal (so you don't need a separate image-to-image model like you did with Qwen-Edit), more coherent, and significantly faster even when outputting at higher 2K resolutions. However, in my testing, I found that I had to play with dialing up the CFG depending on the complexity of the prompt.

I've also added a progress dropdown under Model Performance so you can see how cloud vs. local models have been trending since 2024. Spoiler: June of this year released some of the biggest bangers (Krea 2, Ideogram 4, and the kind of slept-on Boogu-Image 0.1).

Downsides:

- It was clearly trained on at least some level of synthetic training data, and it shows in some of the subpar outputs in terms of fidelity. Some of this you might be able to iron out with a refiner model downstream or a custom LoRA but time will tell.

- They've moved away from the permissive Apache license. Commercial usage is only allowed by request.

Comparisons:

https://genai-showdown.specr.net

If you just want to compare local models only:

http://genai-showdown.specr.net/?models=local

That benchmark might have some issues. You prompted the models to generate an image of striking a ring against a crucible. Then you (presumably, manually?) scored the images that depicted an anvil higher than the ones striking something resembling a crucible.

It would make more sense to compare with Qwen Image 2, since that was the last open weights Qwen model.

Edit: This is wrong.

Native transparency isn’t so hard to do by the way, I made an image AE (I don’t say VAE deliberately as none of these are VAEs, I don’t know why they keep being called that since the variational part is completely absent) that supported this about two years ago as a hobby project. I haven’t really been following the space recently, I’m surprised it’s taken so long for this to come out if it’s a first.

They're trying to cash in but this is just sad

Could you add new OAI 2.5 image models?

Calling open-weights as open-source in marketing materials is the usual misrepresentation. But now with the restriction on commercial use (which is against opensource definition) it is not even open-weights, technically it would be more accurate to call it weights-available.

I'm willing to bet a nonzero amount of its training material is GPL, so I'll treat it as GPL licensed instead and use it however the fuck I want.

If AI labs get to ignore licenses, so do we.

Was going to post about this: the last image models with Apache 2.0 license seem to be from 2025, recent Qwen models are "non-commercial use".

What are the top image models that still use a less restrictive license today?

Tune the weights a bit and call them derivative work.

Those simple prompts produce nearly the exact same layout in the 2 different models?

> The text rendering definitely is much, much better than anything else on the open weights market right now

Really? Because basically everything in those screenshots is completely garbled. I didn't follow it super closely but I thought Ideogram or whatever was really good for this particular use, with actual clear text.

I've played with diffusion models on and off since the first release of Stable Diffusion - just for amusement, without a particular goal.

Recently, I've been helping a friend's wife with some basic vector images for her sewing hobby (she has what is essentially a CNC sewing machine) and have been super-impressed with FLUX.1-Kontext, which I've been running on my Macbook Pro with mflux. Its ability to (for example) take a photo of a human or an animal and return a line drawing which is recognisably them (rather than just a generic similarish image as I've experienced with other models) is excellent.

It's an older model now, but (AIUI) has the text-handling features baked in, and in my various testing is very reliable at giving me the outputs that I want, without the randomness I've experienced previously. It's big and relatively slow (~3 mins per 512x512 image edit on my M1 Max Mac) but excellent to work with. It's also very straightforward to set up, without the harness complexity of e.g. comfyui.

Remember that quality output is a necessary but insufficient property of a generative model.

Prompt-adherence is really hit-or-miss—especially if one lacks the visual vocabulary. Likewise with coding, I find junior devs don't think to prompt re: respecting this-or-that interface, or refactoring to point-free style, etc.

So, as others have said, the artist knows better.

I mean I’m sure it’s the reverse for an artist. They would be less impressed with the image and more impressed with the code quality

I've set it up on my local machine just now, as my first local image diffuser. I can confirm it's very easy.

I tried stable-diffusion.cpp, following its compile guide here[0], and its Qwen Image-2.1 specific instructions here[1]. It works out of the box. I made a test pelican[2]. It took 3 minutes on a CPU.

[0] https://github.com/leejet/stable-diffusion.cpp/blob/master/d...

[1] https://github.com/leejet/stable-diffusion.cpp/blob/master/d...

[2] https://i.ibb.co/yMknC2K/output.png

Additional question is what kind of local hardware would be required for this? 7B parameters sounds very light weight, but I'm not sure. (Edit: The download is 33 GB).

Edit x2: As usual I'm in a twisty maze of pip packages that don't work together, with obscure errors about missing modules, even though I followed the instructions on the page to the letter. I really wish people didn't use Python for this stuff. A simple C/C++ program would be so much better.

I am on AI max 395, comfyUI+qwen models is all you technically need. With today's release, I just built a quick and dirty html that allow simpler prompt use and edits ( via headless comfyui ).. its not bad for a day's work, but a little too unpolished to publish. I would say, try comfyUI first ( complex, but it worked OOTB ).

There is difussion.cpp which is intended for those types of models. I set up krea-2-turbo with the help of ChatGPT 2 months ago, if you have a capable computer that's what I would suggest once it becomes supported.

I am using sd.cpp, which is the cousin of llama.cpp: https://github.com/leejet/stable-diffusion.cpp

it already has day-0 qwen image 2.1 support!

I use opencode + <a decent saas llm> to set up all this new ai generation stuff. GLM-5.3 is my current gun. Safely inside podman containers too because I dont trust this fast moving python eco system at all. Never do I want this running on my main OS.

I have FLUX.2 klein and dev, Ideogram, LaDA-Image and SenseNova locally. Works great. Ive never touched a file.

The days of making container yamls myself is over. I read them but I dont edit anymore.

on the linked GitHub page they list support Diffusers, ComfyUI, vLLM-Omni, SGLang, and LightX2V with links to each

Unsloth Desktop is the easiest way imo. There are already gguf quants of this model, or simply wait until the official one comes out.

Probably ComfyUI is one of the easiest way to get started with local image/video models. Or perhaps vLLM, if they have support for it already, would be something like `vllm serve <model> --omni --port 9080`

why not just as you suggested i.e. https://qwen.readthedocs.io/en/latest/run_locally/llama.cpp.... then get the result either via a UI or wget/curl it back?

Ideogram 4 has been around for a while haha

Just think about how recently we got that feature in the official ChatGPT image gen. And now we have that running locally — assuming that is, I can figure out how to get this running on my Mac — blows my mind.

> In midvalues you will see a slight dot pattern.

Is this not simply some sort of watermark instead of an artifact?

> finally fixed their VAE

Can you share the sources?

Qwen Image 3 was released two months ago: https://qwen.ai/blog?id=qwen-image-3.0 I think you have it confused with another model.

You could try attaching other images as references (I think you can attach a maximum of 10 images). If the attachments can be blurred or sketchy or generic enough, they could be used for generalization.

Try translating your prompt to Chinese first, it seems a lot better at understanding and following Chinese prompts even with the translation hop.

Note that the license on this has this in it:

> You shall not use the Materials for any commercial purpose without obtaining a separate commercial license from us.

It probably will be much cheaper to use than other image models, but it seems that will be up to the whims of Qwen/Alibaba rather than just being the cost of putting it in a cloud provider.

https://github.com/QwenLM/Qwen-Image-2.1/blob/main/LICENSE

The result seems a pretty good representation given the source image wasn't that great. I think that Woody Harrelson comes across much worse.

That "10 Input Images" demo had the faces and clothing mixed up a bit. Woody Harrelson turned into a Kelsey Grammer/Harrelson hybrid.

failure modes are so load bearing.

They always had a fourier space mark in their models even without the VAEs are usually pretty easy to detect.

And they shouldn’t be enforceable considering how the training data was slurped up without concern for licensing.