mixlab visual researcher

What to prepare

Upload a product screenshot/advertising poster/UI screenshot, automatically interpret it based on the text.vision multi-modal model, and output a structured Design.md document: YAML Front Matter at the top defines a machine-readable design token (primary_color / accent_color / font_serif / font_sans / spacing_unit / border_radius), click Overview / Colors / Typography / Layout / Elevation & Depth / Shapes / Components / Do's and Don'ts Eight chapters illustrate design concepts. Design tokens that cannot be inferred will be marked unknown and will never be made up. The new version is based on template-spec/v2 spec and uses the google/gemini-3-flash model.

screenshotRequired

Follow the field instructions to enter your content.

Generation instructions

Each row is submitted as a separate task. Required fields are marked with *.

• Upload a product screenshot, advertising poster or UI screenshot (jpg/png/webp).
• A complete interpretation of Design.md is performed once per line.