CLIPDraw: Exploring Text-to-Drawing Synthesis through Language-Image Encoders
This work enables text-to-drawing synthesis for creative applications, but it is incremental as it adapts existing CLIP technology to a new vector-based optimization task.
The authors tackled the problem of generating drawings from text descriptions without training, using a pre-trained CLIP encoder to optimize vector strokes for similarity, resulting in diverse artistic styles and scalable complexity as stroke count increases.
This work presents CLIPDraw, an algorithm that synthesizes novel 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. Crucially, CLIPDraw operates over vector strokes rather than pixel images, a constraint that biases drawings towards simpler human-recognizable shapes. Results compare between CLIPDraw and other synthesis-through-optimization methods, as well as highlight various interesting behaviors of CLIPDraw, such as satisfying ambiguous text in multiple ways, reliably producing drawings in diverse artistic styles, and scaling from simple to complex visual representations as stroke count is increased. Code for experimenting with the method is available at: https://colab.research.google.com/github/kvfrans/clipdraw/blob/main/clipdraw.ipynb