Tag
An open-source project called Screenshot to Code uses AI to convert screenshots, Figma designs, and screen recordings into functional code, saving time for prototyping and rebuilding interfaces.
MobileForge is a benchmark for project-level multi-screen mobile app generation, evaluating multimodal LLMs on build success, cross-page navigation, visual fidelity, maintainability, and efficiency. Experiments on six frontier multimodal LLMs show current models can compile and reach pages but still struggle with interactive navigation and visual quality.
v0 can now turn a full Figma file into a working app by exploring pages and frames, then building the screens as one app.
Introducing an open-source skill that allows Codex to accurately recreate personal websites from reference images, locking in the design through a five-step workflow before generating code.
Locofy provides an agentic frontend layer that bridges Figma designs with Cursor and Claude, enabling automated design-to-code conversion.
KyrieCheungYep released a Codex/Claude Skill called ky-design-to-html, used to convert UI screenshots or design drafts into high-quality HTML/CSS. It reduces visual discrepancies through a workflow of deconstructing design structure, separating code from assets, canvas adaptation, and browser screenshot verification.
A developer rebuilt an entire agency MVP with admin and client portals in one afternoon using a new tool that integrates design, code, and live UI editing into a single platform, claiming to cut weeks of work down to hours.