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.
https://html.non.io/qwen-comparison/
The text rendering definitely is much, much better than anything else on the open weights market right now. Small text fidelity is quite good. It seems like the text encoder however gets a little bit overloaded with larger prompts - note the presence of hex codes in the design output, those were inputs from the expanded prompt.
I'll be trying a post-training run on this for web design, it has some serious potential.
[1] diffui.ai
Even the artifacts are getting picked up.
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.
https://en.wikipedia.org/wiki/Qwen#List_of_models
Unfortunately, it looks like this model is using a much more restrictive license:
(I mean: outside direct or substantial use of Python, and running the Neural Network in the most efficient way.)
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.
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.
EDIT: It still produces artifacts it's better but unusable for production work. In midvalues you will see a slight dot pattern.
Is this not simply some sort of watermark instead of an artifact?
Can you share the sources?
latents go from 16ch @ 8x compression to 64ch @ 16x, so roughly the same total latent budget but much more channel heavy. It’s also deeper/wider, and the old 2x2 transformer patching is gone.
On some images it still produces artifacts but can't say if it's the transformer or the VAE yet.
> 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.
Excited to see what the future holds for them!
I know a few friends of mine who are running models and are ignoring the licence.
Whether it is AGPL 3.0, or a completely restrictive license, it is going to get broken anyway and be used for commercial purposes.
I don't know anyone who looks at the licenses of the OSS software they are using.
In today’s world OSS is synonymous with "Free" and the AI model providers are proof of that with their training of code, datasets, etc.
So it begs the question, why should we abide by their licenses of their models?
It's just freeware.
If AI labs get to ignore licenses, so do we.
If you were to generate outputs for commercial use, I think it would still violate this research license, but it's not like they are going to know, are they?
That said, I am disappointed that the model is not actually open-weights as I expected based on the headline.
How difficult would it be to use this model to create a second model without licensing issues?
And Krea 2 has a community license [2] that is fairly permissive - I think commercial usage is allowed under $1 million.
Boogu-Image scored 6/15 and Krea 2 scored 7/15 on my GenAI Showdown benchmark [3] - only Ideogram4 eclipses them in terms of local models, but its got a far more restrictive license and the JSON structured inputs can be a pain to work with.
[1] - https://github.com/Boogu-Project/Boogu-Image
[2] - https://www.krea.ai/krea-2-licensing
[3] - https://genai-showdown.specr.net/?models=fd,hd,kd,qi,f2d,zt,...
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 think it will technically run on anything that has enough memory. I just tried it on a standard laptop (dual-channel DDR5), and it took about 3 minutes for a 512x512. If you'd want to run it at interactive speeds, you would want a GPU (one which fits this in VRAM).
> "I really wish people didn't use Python for this stuff. A simple C/C++ program would be so much better."
You mean besides stable-diffusion.cpp ?
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...
it already has day-0 qwen image 2.1 support!
I think that's all Python (not a direct executable).
You could just do (see the "Quick Start") four `pip install` and have a dozen lines script to generate the image. But `llama.cpp` and similar do not require e.g. installing Torch (or PyTorch) - you can use `llama.cpp` on a non-specialized machine.
People can continue to use closed SOTA models to generate outputs for commercial or malicious purposes.
What this research license achieves is that we cannot use this model in applications we publish.
> Currently, we support image, audio and video input.
Image outputs are supported, videos I'm not sure but I don't think that's an output, just a preview of the equirectangular example, so, same question here, what does this model outputs that isn't supported?
It’s more of something to scare companies with legal teams. If you’re an individual or hobbyist doing a side project the risk is essentially zero.
I don't think I have ever once run "pip install transformers" and had it work without three rounds of fiddling
There is no single opinion, and clearly no single Chinese approach.
Also Chinese labs are in particular very careful about anything which be used to create pornographic content, which is highly illegal in the PRC.
MiniMax H3 is dominating AI porn right now, and they are Chinese.
It's not going to matter then, either. What are they going to do, sue me for copyright infringement?
I understand that llama.cpp could only output text, last time I checked (I do not know how to find a good source for that though).
See https://github.com/ggml-org/llama.cpp/blob/master/src/llama-... , the
enum llm_arch {
At the risk of stating the obvious llama.cpp isn't just about LLaMa as https://github.com/ggml-org/llama.cpp/blob/master/src/llama-... someone else pointed out.
Why even bother demanding such terms? Release the weights or don't release the weights, but this is silly. No one is going to pay them to run or host a 7B static image model.