Our great sponsors
-
CLIP
CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image
-
WorkOS
The modern identity platform for B2B SaaS. The APIs are flexible and easy-to-use, supporting authentication, user identity, and complex enterprise features like SSO and SCIM provisioning.
This app uses what's called a generative adversarial neural network to generate images that resemble other images and CLIP (Contrastive Language–Image Pre-training) which is used to assess how well a given image matches a text prompt.
There are various implementations floating around the web which combine VQGAN and CLIP to generate AI artwork (Google Colab or locally using Python). See this list for a more comprehensive overview of projects using VQGAN+CLIP.