AI革命57--双飞燕两种变化的选择，颠覆性的理解

AI 大模型周报 2025年6月 d（附链接）

[ElevenLabs 音色设计] https://elevenlabs.io/voice-design [MiniMax 音色设计] https://www.minimaxi.com/audio/voice-design [ElevenLabss 11ai AI助理] https://elevenlabs.io/blog/introducing-11ai [Dipal D1虚拟伴侣] https://www.dipal.net [AI眼镜Oakley Meta HSTN] https://about.fb.com/news/2025/06/introducing-oakley-meta-glasses-a-new-category-of-performance-ai-glasses [Xiaomi AI 眼镜] https://www.mi.com/prod/xiaomi-ai-glasses?spmref=MiShop_PC.mihomepage.mtl_68268f9e352df300011b9422.1 [Samsung AI Vision] https://www.samsung.com/us/tvs/vision-ai-tv [Anthropic Claude Artifacts] https://www.anthropic.com/news/build-artifacts [Doppl虚拟试装] https://labs.google/doppl [Gemini Robotics On-Device] https://deepmind.google/discover/blog/gemini-robotics-on-device-brings-ai-to-local-robotic-devices [AlphaGenome] https://deepmind.google/discover/blog/alphagenome-ai-for-better-understanding-the-genome [Imagen 4] https://developers.googleblog.com/en/imagen-4-now-available-in-the-gemini-api-and-google-ai-studio [Gemini CLI] https://blog.google/technology/developers/introducing-gemini-cli-open-source-ai-agent

【CVPRW 2025】Arash Vahdat (NVIDIA)

转载自https://www.youtube.com/watch?v=28-sLw55a1s Visual Generative Modeling workshop@CVPR2025, afternoon session 15:30–16:00 What's wrong with diffusion? Speaker: Arash Vahdat (NVIDIA) Workshop website: https://vgm-cvpr.github.io/ About VGM at CVPR 2025 In recent years, diffusion models have rapidly overtaken previous methods to become the dominant approach in visual generative modeling, with widespread applications in generating images, videos, 3D objects, and more. However, these models also come with notable limitations, such as slow generation speeds, limited human intervention during the generation process, and challenges in modeling complex distributions like long videos. This year, our Visual Generative Modeling workshop at CVPR aims to explore what lies beyond diffusion models in visual generative modeling. We will discuss novel insights, alternative approaches, and new possibilities in modeling and generating visual data. Join us for a full-day event featuring keynote talks from both academia and industry -- all designed to ignite innovative ideas and novel research in visual generative modeling. Invited Speakers: Bill Freeman (MIT) Jiajun Wu (Stanford University) Jun-Yan Zhu (CMU) Phillip Isola (MIT) Kaiming He (MIT) Robin Rombach (Black Forest Labs) Jiaming Song (Luma AI) Jiatao Gu (Apple / UPenn) Varun Jampani (Stability AI) Arash Vahdat (NVIDIA) Ricky T. Q. Chen (FAIR) Liang-Chieh Chen (Amazon FAR) Organizers: Tianhong Li (MIT) Yilun Xu (Google DeepMind) Tianyuan Zhang (MIT) Tim Dockhorn (Black Forest Labs) Shuang Li (Stanford University) Arash Vahdat (NVIDIA) Kaiming He (MIT)

通义万相2.1视频模型，图生视频+文生视频本地部署 这可能是目前最详细的wan2.1 安装教程

工作流留言

Ollama连续更新3个版本，终于解决了这些问题！深度解析：性能飞跃、稳定性飞升，AI模型应用更流畅！

给大家准备了一份大模型学习资料包！ 包含了ChatGLM、LLM、LangChain、Lora等大语言模型预训练及微调教程和源码资料、2025最新大模型相关面试题、大模型前沿论文、大模型全流程学习路径等！ 可在评论区置顶获取哦~ 制作不易，各位看官老爷觉得视频对你有帮助麻烦点个关注呀，一键三连呀【点赞、投币、收藏】感谢支持~

浏览器必装的翻译神器！视频翻译、漫画翻译、文件翻译全搞定！打破传统信息差！

告诉我！你有了这个插件，会用来干嘛！ 回答我！look in my eyes！？ 快！ 说！

国外教授开源AI大模型训练代码，从此不再是博士生高端局，AI大佬集体破防【大模型、AI、人工智能、智能体、LLM、大模型微调、Agent】

grok3.5深度测试与测评

-

它把AI画画的天花板又抬高了一截 又一国产AI绘画模型 Chroma v20250609 一键整合包

整合包20250609说明 1 修改了禁止外网分享 2 理论上应该是支持40系和50系显卡（50系未测试AI环境是cuda12.8） 3 生成的图片保存在output文件夹 4 本人觉得这个模型出图质量还是很不错的 5 视后续欢迎程度再考虑是否继续二次开发 6 本人4070ti spuer win11 ltsc +cuda12.4 完美运行 一张图大概一分钟，最低估计要12g显卡。 7 只支持英伟达，别问A卡了。有A卡的 换显卡吧 下载 https://www.jian27.com/html/310.html

20分钟掌握AI大模型！零基础入门，4大必学场景大揭秘！挖掘DeepSeek、ChatGPT的真正潜力！分析图片和文件，输出复杂图表、代码，一次性教会你怎么操作

提示词和角色预设合集：https://gf66fxi6ji.feishu.cn/wiki/AooDweIrNiVOSmkMkmvcpHGtnmd 花了很长时间做的一期大模型入门教程！如果对你有帮助，请一定要一键三连支持一下UP啦！ 希望能对你有帮助！( • ̀ω•́ )✧

读懂字节开源AI框架Eino实现逻辑（第2期）