[ICPRAI 2024] DocumentCLIP: Linking Figures and Main Body Text in Reflowed Documents
-
Updated
Apr 4, 2024 - Python
[ICPRAI 2024] DocumentCLIP: Linking Figures and Main Body Text in Reflowed Documents
This project explores how AI can generate art that balances creativity with following a given prompt. By integrating OpenAI's CLIP model with Creative Adversarial Networks (CANs), the system improves how well generated images match specific content prompts while maintaining artistic diversity.
Inmemory semantic search over images/captions using image and text
Add a description, image, and links to the clipmodel topic page so that developers can more easily learn about it.
To associate your repository with the clipmodel topic, visit your repo's landing page and select "manage topics."