Generating images that fit a given text description using machine learning has improved greatly with the release of technologies such as the CLIP image-text encoder model; however, current methods lack artistic control of the style of image to be generated. We introduce StyleCLIPDraw which adds a style loss to the CLIPDraw text-to-drawing synthesis model to allow artistic control of the synthesized drawings in addition to control of the content via text. Whereas performing decoupled style transfer on a generated image only affects the texture, our proposed coupled approach is able to capture a style in both texture and shape, suggesting that the style of the drawing is coupled with the drawing process itself. More results and our code are available at https://github.com/pschaldenbrand/StyleCLIPDraw
翻译:随着CLIP图像-文本编码器模型等技术的释放,使用机器学习生成符合特定文本描述的图像大有改进;然而,目前的方法缺乏对所生成图像风格的艺术控制。我们引入了StyleCLIPPraw, 给CLIPPraw 文本到绘图合成模型增加了样式损失, 从而除了通过文本控制内容外,还允许对合成图画进行艺术控制。 虽然在生成图像上进行脱钩式传输只会影响纹理,但我们提议的结合方法能够捕捉纹理和形状的风格,表明绘画的风格与绘图过程本身相配合。更多的结果和代码可以在https://github.com/pschaldenbrand/STyCLIPraw上查阅。