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/

▲

copperx 5 hours ago | parent | next [-]

By any chance did you tried Deepseek 4 or 4.1 and GLM 5.3 or flash?

▲

jjcm 5 hours ago | parent [-]

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.

▲

fr33k3y 2 hours ago | parent | next [-]

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...

▲

jjcm 2 hours ago | parent [-]

I should give it a spin. 5.3 wasn't multimodal, but it looks like their flash release was. Thanks for the tip.

	▲	copperx an hour ago \| parent [-]
		Deepseek 4.1 is also multimodal BTW

▲

copperx 4 hours ago | parent | prev [-]

Awesome. You have a really neat benchmark.

▲

naet 6 hours ago | parent | prev [-]

What is your workflow for making these?

	▲	jjcm 5 hours ago \| parent [-]
		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.