Tsallaka zuwa babban abun ciki
Takardu/Explore the complete product/Design and multimodal input

Design and multimodal input

Use supported images, documents, links and voice inputs to describe an interface or a task.

Use the inputs supported by the current conversation and selected model. Describe the purpose, required content and the desired visual result, then inspect the generated files or preview.

Images, URLs, documents and voice have different availability and permission requirements. Upload only material you are authorized to use. Desktop design modes and assistant appearance generation are separate flows; choosing an existing appearance does not imply a new paid generation request.

Open this workspace

View all capabilities