Update on 2024/04/20: We release an advanced version of CLIP-VG, namely HiVG (paper, github). Update on 2023/12/13: All of the code, models and datasets have been released. Update on 2023/9/25: Our paper has been accepted by the top journal IEEE Transaction on Multimedia (2023)!
title: CLIPVG: Text-Guided Image Manipulation Using Differentiable Vector Graphics accepted: AAAI 2023 paper: https://arxiv.org/abs/2212.02122 code: https://github.com/NetEase-GameAI/clipvg ref: https://mp.weixin.qq.com/s/JPpnPqNS8ulb4K9GLBFnHQ 亮点:矢量图、CLIP、无需训练、无生成模型 针...
论文地址:https://arxiv.org/abs/2212.02122 开源代码:https://github.com/NetEase-GameAI/clipvg 部分效果如下(按次序分别为人脸编辑、车型修改、建筑生成、改色、花纹修改、字体修改)。 在生成效果方面,CLIPVG 相比业界已知的其他方案,将语义准确度提高了 15.9%,生成质量提高了 23.6%,即能够自动编辑并输出更贴合...
ok, thank you Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment Assignees No one assigned Labels None yet Projects None yet Milestone No milestone Development No branches or pull requests 2 participants Footer...
Contribute to vgbench/VGBench development by creating an account on GitHub.
github-actions bot added the raster label Nov 11, 2024 RuiwenTang mentioned this pull request Nov 11, 2024 gl_engine: Lottie rendering compatibility #2799 Open 36 tasks hermet assigned RuiwenTang Nov 11, 2024 hermet added the bug label Nov 11, 2024 hermet approved these changes Nov...