92 lines
6.2 KiB
XML
92 lines
6.2 KiB
XML
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 700 350" width="700" height="350">
|
|
<defs>
|
|
<marker id="arrow-red" markerWidth="8" markerHeight="6" refX="8" refY="3" orient="auto">
|
|
<path d="M0,0 L8,3 L0,6" fill="#e74c3c"/>
|
|
</marker>
|
|
<marker id="arrow-blue" markerWidth="8" markerHeight="6" refX="8" refY="3" orient="auto">
|
|
<path d="M0,0 L8,3 L0,6" fill="#3498db"/>
|
|
</marker>
|
|
<marker id="arrow-green" markerWidth="8" markerHeight="6" refX="8" refY="3" orient="auto">
|
|
<path d="M0,0 L8,3 L0,6" fill="#27ae60"/>
|
|
</marker>
|
|
<marker id="arrow-orange" markerWidth="8" markerHeight="6" refX="8" refY="3" orient="auto">
|
|
<path d="M0,0 L8,3 L0,6" fill="#f39c12"/>
|
|
</marker>
|
|
<marker id="arrow-purple" markerWidth="8" markerHeight="6" refX="8" refY="3" orient="auto">
|
|
<path d="M0,0 L8,3 L0,6" fill="#9b59b6"/>
|
|
</marker>
|
|
<marker id="arrow-teal" markerWidth="8" markerHeight="6" refX="8" refY="3" orient="auto">
|
|
<path d="M0,0 L8,3 L0,6" fill="#1abc9c"/>
|
|
</marker>
|
|
</defs>
|
|
|
|
<!-- Title -->
|
|
<text x="350" y="24" text-anchor="middle" font-family="Arial, sans-serif" font-size="14" font-weight="bold" fill="#333">Cross-Modal Generation Pathways</text>
|
|
|
|
<!-- Center hub -->
|
|
<rect x="275" y="145" width="150" height="50" rx="8" fill="#9b59b6" fill-opacity="0.12" stroke="#9b59b6" stroke-width="1.5"/>
|
|
<text x="350" y="175" text-anchor="middle" font-family="Arial, sans-serif" font-size="12" font-weight="bold" fill="#333">Generation Model</text>
|
|
|
|
<!-- Text (top, red) -->
|
|
<rect x="295" y="42" width="110" height="40" rx="8" fill="#e74c3c" fill-opacity="0.12" stroke="#e74c3c" stroke-width="1.5"/>
|
|
<text x="350" y="58" text-anchor="middle" font-family="Arial, sans-serif" font-size="11" font-weight="bold" fill="#e74c3c">Text</text>
|
|
<text x="350" y="72" text-anchor="middle" font-family="Arial, sans-serif" font-size="9" fill="#666">"a sunset over ocean"</text>
|
|
|
|
<!-- Image (right, blue) -->
|
|
<rect x="520" y="150" width="110" height="40" rx="8" fill="#3498db" fill-opacity="0.12" stroke="#3498db" stroke-width="1.5"/>
|
|
<text x="575" y="166" text-anchor="middle" font-family="Arial, sans-serif" font-size="11" font-weight="bold" fill="#3498db">Image</text>
|
|
<text x="575" y="180" text-anchor="middle" font-family="Arial, sans-serif" font-size="9" fill="#666">pixels / latents</text>
|
|
|
|
<!-- Audio (bottom, green) -->
|
|
<rect x="295" y="260" width="110" height="40" rx="8" fill="#27ae60" fill-opacity="0.12" stroke="#27ae60" stroke-width="1.5"/>
|
|
<text x="350" y="276" text-anchor="middle" font-family="Arial, sans-serif" font-size="11" font-weight="bold" fill="#27ae60">Audio</text>
|
|
<text x="350" y="290" text-anchor="middle" font-family="Arial, sans-serif" font-size="9" fill="#666">waveform / spectrogram</text>
|
|
|
|
<!-- Video (left, orange) -->
|
|
<rect x="70" y="150" width="110" height="40" rx="8" fill="#f39c12" fill-opacity="0.12" stroke="#f39c12" stroke-width="1.5"/>
|
|
<text x="125" y="166" text-anchor="middle" font-family="Arial, sans-serif" font-size="11" font-weight="bold" fill="#f39c12">Video</text>
|
|
<text x="125" y="180" text-anchor="middle" font-family="Arial, sans-serif" font-size="9" fill="#666">frame sequence</text>
|
|
|
|
<!-- Arrows: Text <-> Hub (top) -->
|
|
<line x1="335" y1="82" x2="325" y2="145" stroke="#e74c3c" stroke-width="1.2" marker-end="url(#arrow-red)"/>
|
|
<line x1="375" y1="145" x2="365" y2="82" stroke="#e74c3c" stroke-width="1.2" marker-end="url(#arrow-red)"/>
|
|
|
|
<!-- Arrows: Image <-> Hub (right) -->
|
|
<line x1="425" y1="160" x2="520" y2="163" stroke="#3498db" stroke-width="1.2" marker-end="url(#arrow-blue)"/>
|
|
<line x1="520" y1="177" x2="425" y2="180" stroke="#3498db" stroke-width="1.2" marker-end="url(#arrow-blue)"/>
|
|
|
|
<!-- Arrows: Audio <-> Hub (bottom) -->
|
|
<line x1="335" y1="195" x2="325" y2="260" stroke="#27ae60" stroke-width="1.2" marker-end="url(#arrow-green)"/>
|
|
<line x1="375" y1="260" x2="365" y2="195" stroke="#27ae60" stroke-width="1.2" marker-end="url(#arrow-green)"/>
|
|
|
|
<!-- Arrows: Video <-> Hub (left) -->
|
|
<line x1="275" y1="163" x2="180" y2="160" stroke="#f39c12" stroke-width="1.2" marker-end="url(#arrow-orange)"/>
|
|
<line x1="180" y1="180" x2="275" y2="177" stroke="#f39c12" stroke-width="1.2" marker-end="url(#arrow-orange)"/>
|
|
|
|
<!-- Diagonal arrows: Text -> Image -->
|
|
<path d="M400,62 Q490,70 525,150" fill="none" stroke="#9b59b6" stroke-width="1" stroke-dasharray="4,3" marker-end="url(#arrow-purple)"/>
|
|
<text x="478" y="90" text-anchor="middle" font-family="Arial, sans-serif" font-size="8" fill="#9b59b6">text-to-image</text>
|
|
|
|
<!-- Diagonal arrows: Text -> Audio -->
|
|
<path d="M300,72 Q220,160 300,265" fill="none" stroke="#1abc9c" stroke-width="1" stroke-dasharray="4,3" marker-end="url(#arrow-teal)"/>
|
|
<text x="230" y="170" text-anchor="middle" font-family="Arial, sans-serif" font-size="8" fill="#1abc9c">text-to-audio</text>
|
|
|
|
<!-- Diagonal arrows: Text -> Video -->
|
|
<path d="M300,58 Q200,50 140,150" fill="none" stroke="#f39c12" stroke-width="1" stroke-dasharray="4,3" marker-end="url(#arrow-orange)"/>
|
|
<text x="195" y="82" text-anchor="middle" font-family="Arial, sans-serif" font-size="8" fill="#f39c12">text-to-video</text>
|
|
|
|
<!-- Diagonal arrows: Image -> Text -->
|
|
<path d="M575,150 Q560,90 405,55" fill="none" stroke="#e74c3c" stroke-width="1" stroke-dasharray="4,3" marker-end="url(#arrow-red)"/>
|
|
<text x="520" y="82" text-anchor="middle" font-family="Arial, sans-serif" font-size="8" fill="#e74c3c">image-to-text</text>
|
|
|
|
<!-- Diagonal arrows: Image -> Video -->
|
|
<path d="M520,180 Q400,250 180,185" fill="none" stroke="#f39c12" stroke-width="1" stroke-dasharray="4,3" marker-end="url(#arrow-orange)"/>
|
|
<text x="380" y="240" text-anchor="middle" font-family="Arial, sans-serif" font-size="8" fill="#666">image-to-video</text>
|
|
|
|
<!-- Diagonal arrows: Audio -> Text -->
|
|
<path d="M400,270 Q490,240 560,190" fill="none" stroke="#e74c3c" stroke-width="1" stroke-dasharray="4,3" marker-end="url(#arrow-red)"/>
|
|
<text x="510" y="250" text-anchor="middle" font-family="Arial, sans-serif" font-size="8" fill="#666">audio-to-text</text>
|
|
|
|
<!-- Legend -->
|
|
<text x="350" y="330" text-anchor="middle" font-family="Arial, sans-serif" font-size="9" fill="#999">Solid lines = primary pathways | Dashed lines = direct cross-modal translation</text>
|
|
</svg> |