Something that's not mentioned here is that for design agencies who work as multiple clients, the app has the ability to save and work with multiple brand profiles. You can upload a bunch of screenshots of examples of the brand's design language - from their app or website or ads or whatever - and have Diffui make a brand guide just based on that, and then any future designs are influenced by that brand guide. Pretty neat little trick.
Thank you! That effect is easier than you'd think. Normal maps/depth maps are actually fairly easy to generate via diffusion models. Once I had the designs for the tarot site in diffui, I just copied the build plan, pasted it into claude, and asked it to "generate normal/depth/roughness maps for each of the card designs and dynamically light and displace them based on the mouse position."
The build plan has tooling built in to generate these. Under the hood the model I'm routing to is Fal.ai's Patina model, which does a fantastic job at creating maps.
Exactly right. You design with the diffusion model, then hand those designs off to an agent to implement.
It's a lot like having an architect create plans for you before handing it off to a builder. In my (obv biased) experience, you end up getting better/more creative results with this approach. You're using the best model for the job at each specific task, ie a diffusion model as the designer, and a LLM as the engineer.
Something that's not mentioned here is that for design agencies who work as multiple clients, the app has the ability to save and work with multiple brand profiles. You can upload a bunch of screenshots of examples of the brand's design language - from their app or website or ads or whatever - and have Diffui make a brand guide just based on that, and then any future designs are influenced by that brand guide. Pretty neat little trick.
I got an early tip on this and used it to build a brand mood board and it crushed previous attempts with Claude. Highly recommend.
The Tarot card example on here is so sick.
Thank you! That effect is easier than you'd think. Normal maps/depth maps are actually fairly easy to generate via diffusion models. Once I had the designs for the tarot site in diffui, I just copied the build plan, pasted it into claude, and asked it to "generate normal/depth/roughness maps for each of the card designs and dynamically light and displace them based on the mouse position."
The build plan has tooling built in to generate these. Under the hood the model I'm routing to is Fal.ai's Patina model, which does a fantastic job at creating maps.
File is here btw if you want to explore: https://diffui.ai/app/canvas/be49d1a3-df57-4c61-9305-4aef472...
I had this redesign my new landing page. Excited to see how this develops
Okay so the diffusion model generates image assets, and you iterate on those, and then another model turns your favorites into code, is that right?
Exactly right. You design with the diffusion model, then hand those designs off to an agent to implement.
It's a lot like having an architect create plans for you before handing it off to a builder. In my (obv biased) experience, you end up getting better/more creative results with this approach. You're using the best model for the job at each specific task, ie a diffusion model as the designer, and a LLM as the engineer.