随笔分类 -  AIGC

Transfusion: Predict the Next Token and Diffuse Images with One Multi-Modal Model(2024,8)
摘要：Transfusion: Predict the Next Token and Diffuse Images with One Multi-Modal Model(2024,8) Paper TODO: 目前没有开源代码,实时关注一下official code,Meta的工作基本开源的.本文给出了一 阅读全文
posted @ 2024-09-04 23:02 chenfengshijie 阅读(350) 评论(0) 推荐(1)
RestoreFormer++: Towards Real-World Blind Face Restoration from Undegraded Key-Value Pairs(IEEE,2023,8)
摘要：RestoreFormer++: Towards Real-World Blind Face Restoration from Undegraded Key-Value Pairs(IEEE,2023,8) Paper GitHub 动机:认为之前的模型都只关注了图像的纹理信息,而忽视了人脸的细节信 阅读全文
posted @ 2024-09-04 22:55 chenfengshijie 阅读(97) 评论(0) 推荐(0)
ControlNeXt: Powerful and Efficient Control for Image and Video Generation(2024,8)
摘要：ControlNeXt: Powerful and Efficient Control for Image and Video Generation(2024,8) paper Github 进一步在ControlNet上进行了改进,主要针对一下两点 对于每一个模块添加一个Zero-Conv也会占用 阅读全文
posted @ 2024-08-19 21:22 chenfengshijie 阅读(130) 评论(0) 推荐(0)