CLIP and PASTE: Using AI to Create Photo Collages from Text Prompts

How to use ML models to extract objects from photographs and rearrange them to create modern art

By Robert. A Gonsalves</br>

You can see my article on Medium.

The source code and generated images are released under the CC BY-SA license.</br>

Google Colabs

• CLIP and PASTE

Acknowledgements

• CLIP by A. Radford et al., Learning Transferable Visual Models From Natural Language Supervision (2021)
• F. Boudin, PKE: An Open-Source Python-based Keyphrase Extraction Toolkit (2016), Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: System Demonstrations
• Wikimedia Commons (2004-present)
• OpenImages (2020)
• GRoIE by L. Rossi, A. Karimi, and A. Prati, A Novel Region of Interest Extraction Layer for Instance Segmentation (2020)
• D. P. Kingma and J. Lei Ba, Adam: A Method for Stochastic Optimization (2015), The International Conference on Learning Representations 2015
• M. Grootendorst, KeyBERT: Minimal keyword extraction with BERT (2020)
• E. Riba, D. Mishkin, D. Ponsa, E. Rublee, and G. Bradski, Kornia: an Open Source Differentiable Computer Vision Library for PyTorch (2020), Winter Conference on Applications of Computer Vision

Citation

To cite this repository:

@software{CLIP and PASTE,
  author  = {Gonsalves, Robert A.},
  title   = {CLIP and PASTE: Using AI to Create Photo Collages from Text Prompts},
  url     = {https://github.com/robgon-art/CLIPandPAST},
  year    = 2022,
  month   = June
}