IconShop: Text-Guided Vector Icon Synthesis with Autoregressive Transformers
Ronghuan Wu
,
Wanchao Su
,
Kede Ma
,
Jing Liao
City University of Hong Kong
SIGGRAPH Asia 2023
Paper
Code
Vector icons generated with text prompts. The proposed IconShop supports vector icon synthesis from
keywords
(left panel) and
natural phrases and sentences
(right panel).
Random Generation
Text-Guided Generation
Icon Editing
Semantic Combination of Icons
Icon Interpolation
Auto-Suggestion (Voice-over)