surface↓visualization↓stylize
Visualizationpipeline · returns table

STYLIZE

Artistically stylize a chart image while preserving data

Table-in, table-out — composes downstream of SELECTs.

visualizationllmpipeline-composableimage

Syntax

THEN STYLIZE {{ prompt }}
THEN STYLIZE({{ prompt }})
THEN STYLIZE({{ prompt }}, {{ fidelity }})

Arguments

nametypedescription
promptVARCHAR—
fidelity(optional)FLOAT—
_tableTABLE—

About

PIPELINE cascade for artistic stylization of chart images. Takes a rendered chart image and uses an image-capable LLM to repaint it with artistic style while preserving the data representation. The input image acts as grounding - spatial layout and data proportions are preserved, only the rendering style changes. Usage: SELECT * FROM data THEN TO_PLOTLY 'bar chart' THEN RENDER THEN STYLIZE 'watercolor painting style' THEN STYLIZE('futuristic neon glow', 0.9) -- with fidelity Fidelity (0.0-1.0): 1.0 = exact structure preservation 0.5 = moderate artistic interpretation 0.0 = loose creative interpretation

Examples

Produces a stylized image while preserving the chart payload shape

SELECT
  *
FROM
  (
    SELECT
      'plotly' AS format,
      '{"type":"bar","x":"category","y":"amount"}'::JSON AS config,
      'A' AS category,
      10 AS amount
    UNION ALL
    SELECT
      'plotly',
      '{"type":"bar","x":"category","y":"amount"}'::JSON,
      'B',
      20
  ) THEN RENDER (300, 200, 1) THEN STYLIZE ('watercolor painting style', 0.9) THEN PYTHON (
    'image = str(df.iloc[0].get("image", "")) if len(df) else ""; result = pd.DataFrame({"ok":["image" in df.columns and image.startswith(("data:image/", "/api/images/"))]})'
  )

Nearby rabbit holes

same domain
pipeline

MERMAID_TIMELINE

Convert timeline data to Mermaid timeline visualization

visualizationllmpipeline-composabletext
pipeline

MERMAID_TRIPLES

Convert triples to Mermaid graph visualization

visualizationllmpipeline-composabletext
pipeline

RENDER

Render a chart specification to PNG image

visualizationllmpipeline-composableimage
pipeline

TO_PLOTLY

Generate a Plotly chart from data using LLM

visualizationllmpipeline-composabletext
pipeline

TO_PROPERTY_GRAPH

Convert triples to relational node/edge graph tables for recursive CTE traversal

visualizationllmpipeline-composabletext
pipeline

TO_VEGALITE

Generate a Vega-Lite chart from data using LLM

visualizationllmpipeline-composabletext
Climb back to The Looking Glass