# CLIPVG: Text-Guided Image Manipulation Using Differentiable Vector Graphics Source: [CLIPVG: Text-Guided Image Manipulation Using Differentiable Vector Graphics]() Collection index: [llms.txt]() Data updated: 2025-10-26T01:17:36.551Z Authors: Yiren Song, Xuning Shao, Kang Chen, Weidong Zhang, Minzhe Li, Zhongliang Jing Published: 2022-12-05T09:29:31.000Z ## Abstract Considerable progress has recently been made in leveraging CLIP (Contrastive Language-Image Pre-Training) models for text-guided image manipulation. However, all existing works rely on additional generative models to ensure the quality of results, because CLIP alone cannot provide enough guidance information for fine-scale pixel-level changes. In this paper, we introduce CLIPVG, a text-guided image manipulation framework using differentiable vector graphics, which is also the first CLIP-based general image manipulation framework that does not require any additional generative models. We demonstrate that CLIPVG can not only achieve state-of-art performance in both semantic correctness and synthesis quality, but also is flexible enough to support various applications far beyond the capability of all existing methods. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Text-guided Portrait Sketch Manipulation on CelebA-HQ Full Image](): Text-guided portrait sketch manipulation; CelebA-HQ Full Image; Accuracy: 76.4. - [Text-guided portrait sketch manipulation on CelebA-HQ Region of Interest](): Text-guided portrait sketch manipulation; CelebA-HQ Region of Interest; Accuracy: 63.1. ## Original sources and implementation [Original paper]() [PDF]()