AI Redraw as SVG
🤖 AI Drafted (Not reviewed)
An AI vision model REDRAWS each image/page as SVG — a generative sketch of the document’s layout and text, not a vector trace of the original image; positions and shapes are approximate. Feeds the SVG (WebKit) representation in the document viewer. The model alias is editable on the Convert node.
| Folder | /Convert |
| Steps | 2 |
| Tags | preset, convert, svg, representation |
Steps, in run order
1. Files
Tool: Files — Pass through input files from workflow context
2. AI Redraw as SVG
Tool: AI Convert — Generative format conversion: an AI vision model re-creates the page as Markdown, HTML, SVG, LaTeX, or CSV. The output is the model’s reading of the page, not a mechanical file conversion.
Settings this step uses:
| Option | Value |
|---|---|
preserve_layout |
yes |
target_format |
svg |
What this step asks the model:
Recreate this image as SVG (Scalable Vector Graphics).
- Reproduce the exact visual layout and positioning
- Use appropriate SVG elements (rect, circle, path, text, g, etc.)
- Set viewBox to match the original dimensions/aspect ratio
- Use colors and fonts that match the original
- Position elements to match their exact locations in the original
- Represent text as <text> elements at correct positions
IMPORTANT: Faithfully reproduce the original layout, spacing, and visual structure. Match positions, alignment, and proportions as closely as possible.
Output ONLY the SVG content, no explanations or code fences.