@article{clipcontrastivelanguageimage2021,
  title = {Learning Transferable Visual Models From Natural Language Supervision (CLIP)},
  author = {Radford, A. and Kim, J. W. and Hallacy, C. and Ramesh, A. and Goh, G. and Agarwal, S. and Sastry, G. and Askell, A. and Mishkin, P. and Clark, J. and Krueger, G. and Sutskever, I.},
  year = {2021},
  journal = {ICML 2021},
  url = {https://arxiv.org/abs/2103.00020},
  abstract = {Radford et al. (2021) trained a model to align image and text representations in a shared embedding space using contrastive learning on 400 million web-scraped image-caption pairs. The resulting CLIP model can match images to natural-language descriptions with strong zero-shot performance. CLIP is the component that allows text prompts to steer image-generation models: Stable Diffusion, DALL-E and CLIP-guided diffusion all depend on its joint embedding to translate a prompt into the visual direction for the generative process. Explaining prompt-to-image generation to animation students requires understanding CLIP's role as the semantic bridge between language and image space.},
  keywords = {generative-ai, image-generation, ai-literacy},
  note = {AI \& Animation Education Knowledge Base}
}