# Diffui

AI UI design tool that generates several interface designs in parallel from a prompt and hands them off to coding agents.

- Website: https://diffui.ai/
- Listing: https://openack.co/p/diffui
- Not evaluated. Listed by OpenACK: its 8 claimed capabilities are OpenACK's reading of the product's public site, not the maker's word, and nobody has checked them yet.

OpenACK's description (not checked):

> Diffui generates interface designs with a diffusion model on a canvas. You prompt for a page, pick among options, extend it into more pages in the same style, save a visual style as a reusable brand, and copy a build package for a coding agent to implement the designs.

## Capabilities

- **not evaluated**: Generate UI designs with AI from a prompt
- **not evaluated**: Generate another page in the same style from an existing design
- **not evaluated**: Paste a screenshot and design a new page in its style
- **not evaluated**: Create a reusable brand from designs or screenshots
- **not evaluated**: Generate designs using a saved brand
- **not evaluated**: Generate linked pages by double-clicking pages shown in a design
- **not evaluated**: Copy a build package for a coding agent
- **not evaluated**: Connect an AI assistant over MCP

## What the statuses mean

- **confirmed** (ACK): a person from OpenACK signed in with a test account and saw it work.
- **not confirmed** (NAK or ?): it was tried and didn't work, or we couldn't reach or check it. Not proof it's missing, but not verified.
- **not evaluated** (—): nobody has checked it. It's the founder's word only.

Treat only "confirmed" as verified. A result is a record of one evaluation on the date shown, not a guarantee.