Comment by jjcm
6 hours ago
Image->HTML tests:
Design: https://image.non.io/78795662-8bfc-4e14-8d72-3738392aa6b3.we...
Opus 5.5's output: https://html.non.io/annui-opus/
Overall it follows image designs quite well, but it did ignore asks to animate page transitions. Additionally it's the least performant of the ones I've built with Astra/Grok/MiMo, despite using a lot of the same code. I'd rate it just below Astra in capability, but still solidly second place.
For comparison with other drops this week + current #1:
Astra: https://html.non.io/annui/
MiMo: https://html.non.io/annui-mimo/
Grok 4.7: https://html.non.io/Annui-grok/
By any chance did you tried Deepseek 4 or 4.1 and GLM 5.3 or flash?
I've done GLM 5.3 previously here: https://news.ycombinator.com/item?id=49295420
Worth noting though that GLM 5.3 isn't multi-modal, so it doesn't have a vision layer. It is quite clever and hacks around it pretty effectively however. I'm running a deepseek 4 build now and will reply shortly with that.
glm5.3-flash is multimodal and I\ve been testing it against opus over the last ~10 days and it does very well at a fraction of the opus price...
2 replies →
Awesome. You have a really neat benchmark.
What is your workflow for making these?
The designs are outputs from my own site. This has an overview of the process: https://diffui.ai/learn/new-site
The gist of it though is I take a prompt, expand it into a json blob specifying structure/palette/positioning of elements/etc, feed that into a diffusion model to output a few choices. Once I lock in a choice I take the pixel output + json blob and use it as input into followup pages. The json helps preserve the brand across multiple pages.
Once I have all the inputs I take their corresponding image+json blobs and feed them into an agent to create a web implementation.
For image models, diffui currently uses gpt-image-2.5, mai-image-2.6, and very, very rarely a post-trained version of flux 2 dev I've made for web design, though that one will be deprecated soon.