I run a prompt-to-ui design site that uses image models for the design process[1]. The text rendering especially makes this model deeply interesting to me, despite the license. Here are some tests using my harness comparing the outputs of gpt-image-2 and qwen 2.1:
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.
Totally normal for modern models due to training on the same datasets supplied by third parties, dataset contamination, and mode collapse, especially for simple prompts that don't have enough semantic capacity. -isms are often very similar even without distillation, and tend to come and go in waves along with model generations.
jjcm · · focus · HN ↗
<a href="https://html.non.io/qwen-comparison/" rel="nofollow">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
cloudking · · focus · HN ↗
orbital-decay · · focus · HN ↗