Personalizing Text-to-Image Generation using Textual Inversion
image-20230918160805170
3-5
张用户提供的概念图像,可以是某一类物体,亦或是某一种风格,就可以在冻结的文生图模型的嵌入空间中学习一种新的关键词(也就是创造了一种新的且和图像对应的提示词prompt)image-20230918164914698
image-20230918164253786
A photo of S*
生成S*图像image-20230918165145512
with S*
生成S*和其他提示词合成的图像image-20230918165247961
in the style of S*
image-20230918165429131
image-20230918165815513
Below we provide the list of text templates used when optimizing a pseudo-word:
• “a photo of a S∗.”,
• “a rendering of a S∗.”,
• “a cropped photo of the S∗.”,
• “the photo of a S∗.”,
• “a photo of a clean S∗.”,
• “a photo of a dirty S∗.”,
• “a dark photo of the S∗.”,
• “a photo of my S∗.”,
• “a photo of the cool S∗.”,
• “a close-up photo of a S∗.”,
• “a bright photo of the S∗.”,
• “a cropped photo of a S∗.”,
• “a photo of the S∗.”,
• “a good photo of the S∗.”,
• “a photo of one S∗.”,
• “a close-up photo of the S∗.”,
• “a rendition of the S∗.”,
• “a photo of the clean S∗.”,
• “a rendition of a S∗.”,
• “a photo of a nice S∗.”,
• “a good photo of a S∗.”,
• “a photo of the nice S∗.”,
• “a photo of the small S∗.”,
• “a photo of the weird S∗.”,
• “a photo of the large S∗.”,
• “a photo of a cool S∗.”,
• “a photo of a small S∗.”
mask
替换S* (图像编辑)A photo of S*
生成S*图像xxx S* xxx
生成S*和其它合成的图像in the style of S*
生成S*风格的图像本文分享自 iResearch666 微信公众号,前往查看
如有侵权,请联系 cloudcommunity@tencent.com 删除。
本文参与 腾讯云自媒体同步曝光计划 ,欢迎热爱写作的你一起参与!