AI creative assistant
Discuss the audience, message and visual direction before creating. The assistant can work with reference images and supported documents, research the web, generate images and export documents in the same conversation. It also supports outfit design, clothing breakdown images, virtual try-on and multi-angle looks.
Open toolUpdated
- What you provide
- A goal or question, optional reference images and supported documents.
- What you get
- A creative plan, answers with source links when researched, images or downloadable documents.
How to use it
- Describe the outcome, audience and constraints. Mention what must stay unchanged.
- Review the proposed direction and any research sources; add references where useful.
- Ask for the image or document you need, then refine the result in the conversation.
- For fashion images, tell the assistant whether you want outfit design, clothing analysis, virtual try-on or multiple angles, and specify the image count. Attach the source photos needed for try-on or analysis.
- Right-click a conversation in the history list, or open More on mobile, to archive it or import it to the infinite canvas. View and restore conversations under Archived on the history page.
Common questions
Do I need a finished prompt?
No. Begin with an idea and ask the assistant to help specify the subject, style, format and intended use.
Can I continue an existing project?
Yes. Reopen its conversation to work with that context, or send selected canvas images and notes to its linked assistant.
Can it generate outfit photos and then matching breakdown images?
Yes. State the total number of photos and breakdown images in one request. The assistant retains the full delivery plan and continues from actual generated images while budget and source availability allow. It reports failures or unfinished items. Each generated image is billed for actual usage.