CLIPDraw: Exploring Text-to-Drawing Synthesis through Language-Image Encoders


Kevin Frans, L.B. Soros, Olaf Witkowski, arXiv, Jul 02, 2021

File this one under 'AI-generated content'. "CLIPDraw is an algorithm that synthesizes stroke-based drawings based on natural language input. CLIPDraw does not require any training; rather a pre-trained CLIP language-image encoder is used as a metric for maximizing similarity between the given description and a generated drawing." Here's the Arxiv Paper (9 page PDF) and here's the Blog Post. Good-by clip art, hello Airt.

New term alert: Airt. (ɛərt) Art created by an AI, typically based on a verbal or textual description. Eyt: term coined by me, but when I looked it up to see if it's new (it is) the meaning resonates really well with the Scots term 'airt'.


Web: [Direct Link] [This Post]

Older Post Newer Post