论文标题
通过美学梯度个性化文本对图像生成
Personalizing Text-to-Image Generation via Aesthetic Gradients
论文作者
论文摘要
这项工作提出了美学梯度，这是一种通过指导用户从一组图像定义的自定义美学的生成过程来个性化剪辑条件扩散模型的方法。使用最新的稳定扩散模型和几个美学过滤数据集，通过定性和定量实验验证该方法。代码在https://github.com/vicgalle/stable-diffusion-aesthethethic-Gradients上发布
This work proposes aesthetic gradients, a method to personalize a CLIP-conditioned diffusion model by guiding the generative process towards custom aesthetics defined by the user from a set of images. The approach is validated with qualitative and quantitative experiments, using the recent stable diffusion model and several aesthetically-filtered datasets. Code is released at https://github.com/vicgalle/stable-diffusion-aesthetic-gradients
