[2106.14843] CLIPDraw: Exploring Text-to-Drawing Synthesis through Language-Image Encoders

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: this https URL

CLIPDraw: Exploring Text-to-Drawing Synthesis through Language-Image Encoders Kevin Frans1,2 , L. B. Soros1 and Olaf Witkowski1,3,4 1 Cross Labs, Cross Compass Ltd., Tokyo, Japan 2…

related reading

• Circuit Tracing: Revealing Computational Graphs in Language Modelstransformer-circuits.pub
• CLIPasso: Semantically-Aware Object Sketchingclipasso.github.io
• CLIP · Hugging Facehuggingface.co
• [2301.13823] Grounding Language Models to Images for Multimodal Generationarxiv.org
• [2103.00020] Learning Transferable Visual Models From Natural Language Supervisionarxiv.org
• 2306.16934.pdfarxiv.org
• [2305.10973] Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifoldarxiv.org
• 2403.09611.pdfarxiv.org
• 2310.01405.pdfarxiv.org
• [2210.13382] Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Taskarxiv.org
• 2310.01405arxiv.org
• [2309.10668] Language Modeling Is Compressionarxiv.org