Papers by Chetan Naik
Generating Contextual Images for Long-Form Text (2024.lrec-main)
Copied to clipboard
| Challenge: | Recent advances in Text-to-Image models require short prompts that describe both the content and style of the target image. |
| Approach: | They propose to use Large Language Models (LLMs) and Text-to-Image Models to synthesize relevant visual imagery from generic long-form text. |
| Outcome: | The proposed models can generate high-quality images from short prompts that describe both the content and style of the target image. |