郭新晨 - 博客园

2025年10月31日

MAGREF: Generate AI Videos with Multiple People and Objects from Images

摘要： https://learn.thinkdiffusion.com/magref-generate-ai-videos-with-multiple-people-and-objects-from-images/#:~:text=MAGREF%20lets%20you%20create%20videos 阅读全文

posted @ 2025-10-31 13:57 郭新晨阅读(3) 评论(0) 推荐(0)

DanceTogether! Identity-Preserving Multi-Person Interactive Video Generation

摘要： https://dancetog.github.io/ 阅读全文

posted @ 2025-10-31 13:53 郭新晨阅读(4) 评论(0) 推荐(0)

NanoVoice: Efficient Speaker-Adaptive Text-to-Speech for Multiple Speakers

摘要： https://nanovoice.github.io/ 阅读全文

posted @ 2025-10-31 13:52 郭新晨阅读(5) 评论(0) 推荐(0)

A CLI text-to-speech tool using the Kokoro model, supporting multiple languages, voices (with blending), and various input formats including EPUB books and PDF documents.

摘要： https://github.com/nazdridoy/kokoro-tts 阅读全文

posted @ 2025-10-31 13:51 郭新晨阅读(4) 评论(0) 推荐(0)

Frontier Open-Source Text-to-Speech

摘要： https://github.com/microsoft/VibeVoice 阅读全文

posted @ 2025-10-31 13:50 郭新晨阅读(2) 评论(0) 推荐(0)

Official PyTorch implementation of One-Minute Video Generation with Test-Time Training

摘要： https://github.com/test-time-training/ttt-video-dit 阅读全文

posted @ 2025-10-31 13:42 郭新晨阅读(4) 评论(0) 推荐(0)

About LongLive: Real-time Interactive Long Video Generation

摘要： http://ithub.com/NVlabs/LongLive 阅读全文

posted @ 2025-10-31 13:42 郭新晨阅读(7) 评论(0) 推荐(0)

2025年10月14日

A curated list of recent diffusion models for video generation, editing, and various other applications.

摘要： https://github.com/showlab/Awesome-Video-Diffusion 阅读全文

posted @ 2025-10-14 12:13 郭新晨阅读(6) 评论(0) 推荐(0)

2025年9月28日

计算机核心课

摘要：别再瞎学了！计算机科学10门核心课，才是真“硬通货” 身边总有计算机专业的同学陷入“无效努力”：刷了300道算法题，面试时被问“红黑树的插入逻辑”却答不上；跟风学了Python爬虫、Vue框架，做项目时连“内存溢出怎么排查”都搞不懂；甚至临近毕业，还分不清“TCP和UDP的区别”——最后简历石沉大海阅读全文

posted @ 2025-09-28 22:02 郭新晨阅读(59) 评论(0) 推荐(0)

使用Python网络爬虫抓取牛客网题目

摘要： https://blog.csdn.net/qq_41729780/article/details/106184970 阅读全文

posted @ 2025-09-28 21:29 郭新晨阅读(10) 评论(0) 推荐(0)

公告