> For the complete documentation index, see [llms.txt](https://xfigura.gitbook.io/xfigura-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://xfigura.gitbook.io/xfigura-docs/tools/visione.md).
# Visione
Use Visione to refine prompts, research references, and build workflows from the xFigura canvas.
Visione is the assistant available from the xFigura canvas. Describe the result you want, use its tools to prepare inputs, and create a workflow without manually placing every node first.
## Start a request
1. Open Visione from the canvas.
2. Enter a request in plain language or choose one of the prompts shown in the interface.
3. Review the proposed workflow and any credit estimate presented for the run.
4. Generate when you are ready.
In **Manual** mode, review the generated workflow before choosing to run it.
## Available tools
* **Enhance Prompt** refines a text prompt before generation.
* **Caption Image** creates a description of an image on the canvas.
* **Node Selector** identifies nodes for a requested task.
* **Workflow Generator** builds a connected workflow from a description.
* **Web Search** finds references and information without leaving the canvas.
## Work with files and research
* Attach files from the staging tray before sending a request.
* Drag a web-search result from Visione onto the canvas.
* Reopen prior chats with their images and attachments.
* From a fully generated node, use the **+** menu to add an available 3D model to the workflow.
## Example workflow
**Parametric lounge chair**
Generate a detailed image of a parametric lounge chair made of interlocking plywood layers with smooth organic curvature. Enhance material realism to highlight wood grain, light reflection, and joinery precision. Use the completed image to create a 3D version for a full rotation view and, in a separate branch, a short video where soft studio lighting moves across the scene.
