


Yesterday, Kunlun Wanwei’s large-scale AI music generation model “Tiangong SkyMusic” launched a free test invitation event. The media, industry experts and interested music practitioners are sincerely invited to experience SOTA's music model products. This product enables users to have an immersive experience while experiencing the emotional expression of human voices together.
After the invitation test started, the majority of users have high expectations for the "Tiangong SkyMusic" AI music generation large model. The staff received hundreds of thousands of test applications in a very short period of time, including many professional music creators, media and industry experts. At the same time, a large number of test applications are continuously sent to the backend. Among the applications, there are many professional music creators, media and industry experts, and there are also a large number of test applications that need to be continuously screened and reviewed. Many of the applicants include many professional music creators, media and industry experts, who continued to provide valuable feedback and opinions during the testing process
At the same time , we have also received a lot of real feedback and high praise from users:
"The vocals are very clear and the lyrical melody is good"
"It sounds great!"
"This is made by heaven?? It's amazing!"
"The song "Wukong" is sung with a sense of breath. , the emotions are very good, and it basically represents the pinnacle of the ability to generate emotions and make it look real."
"Tiangong SkyMusic's high-pitched singing skills are beyond my imagination, very excellent."
"It's too powerful. 1. The user base of AI music is very large; 2. The generated music can be used repeatedly; 3. It is easy to do social fission"
"The chorus part is so smooth and the beat is so good"
"I didn't expect that the Chinese team could make something better than foreign ones"
User AI Music Generation Works
Since the enthusiastic feedback from the majority of users has shown us the industry’s high expectations for the "Tiangong SkyMusic" AI music generation large model, it has also allowed us to see the progress in In the exploration direction of AGI large models focusing on "intelligence", the importance of "emotional AGI" is important.
Compared with text and pictures, audio content is the best way to understand human emotions, and music is the most abundant content carrier for expressing human emotions and the most unrestricted by region and culture. No matter the changes of the times, no matter the Whether it is war or disaster, people can always convey their feelings and obtain emotional comfort through music. This is the original intention of "Tiangong SkyMusic", and it is also an important direction that Kunlun Wanwei Emotion AGI continues to explore.
We would like to thank all users who actively participated and gave enthusiastic feedback. Thank you for your support, encouragement and companionship. We will continue to iterate, optimize and broaden the capabilities of "Tiangong SkyMusic" to make the model more powerful. Multi-modal emotional understanding and expression capabilities bring users a better AI music experience.
Finally, we will soon provide the "Tiangong SkyMusic" music creation prompt guide, and provide more AI music demos and usage techniques, so as to explore the powerful charm of AI music with users!
About "Tiangong SkyMusic" and "Tiangong 3.0"
"Tiangong SkyMusic" AI music generation large model is based on Kunlun Wanwei "Tiangong 3.0" Super large model creation. On April 17, "Tiangong SkyMusic" will open public beta simultaneously with "Tiangong 3.0".
Application webpage: https://rg975ojk5z.feishu.cn/share/base/form/shrcnTcBRpGzv5Sx9xAGd5V97Md
"Tiangong 3.0" uses a 400 billion-level parameter MoE hybrid expert model , and will be simultaneously selected as open source. It is one of the MoE models with the largest model parameters and the strongest performance in the world. Compared with the previous generation "Tiangong 2.0" MoE large model, "Tiangong 3.0" has amazing performance improvements in areas such as model semantic understanding, logical reasoning, versatility, generalization, uncertainty knowledge, and learning capabilities. Its model technical knowledge ability has increased by more than 20%, and its mathematics/reasoning/coding/cultural and creative abilities have increased by more than 30%. At the same time, "Tiangong 3.0" has added the ability to search enhancements, research modes, call codes and draw charts, call online searches multiple times, etc., and has trained the agent capabilities of the model in a targeted manner, so that "Tiangong 3.0" can independently complete Plan, call, and combine external tools and information to accurately and efficiently complete various complex needs such as industrial analysis and product comparison, bringing a new disruptive artificial intelligence experience.
"Tiangong SkyMusic" is currently the first and only publicly available large-scale AI music generation model in China. It adopts a Sora-like model architecture in the music audio field, and Large-scale Transformer is responsible for composing music. , to learn the contextual dependencies of Music Patches and achieve music controllability; Diffusion Transformer is responsible for singing and restoring Music Patches into high-quality audio through LDM, so that "Tiangong SkyMusic" can support the generation of 80 seconds 44100Hz sampling rate dual sound stereo songs. This model architecture works extremely well in the fields of video, audio, and music. The Kunlun Wanwei team will also gradually iterate and add new capabilities in the future, so that the model has multi-modal emotional understanding and expression capabilities.
"Tiangong SkyMusic" test application website: https://rg975ojk5z.feishu.cn/share/base/form/shrcnTcBRpGzv5Sx9xAGd5V97Md
"Tiangong SkyMusic" has the following five characteristics:
1. High-quality AI music
"Tiangong SkyMusic" can generate 80 seconds 44100Hz sampling rate two-channel stereo AI songs, and can generate corresponding song styles according to the lyrics style input by the user .
2. Human voices are "fake and real"
Vocal synthesis is the most important dimension in AI music generation that best reflects the generation effect and quality. The AI vocal synthesis of "Tiangong SkyMusic" can reach the industry's top SOTA level. The Chinese proficiency is extremely good, and the pronunciation is clear and no abnormal noise. Its Chinese singing effect is significantly better than that of foreign products, leading the world level.
3. Lyric paragraph control
"Tiangong SkyMusic" can control songs through lyrics, so that the generated songs can clearly distinguish the emotional changes of different lyric paragraphs. Reflect the differences between verses and chorus, intro and verse.
4. Various music styles
"Tiangong SkyMusic" supports rap, folk, funk, ancient style, electronic and other music styles. Users are creating music , you can use the reference audio to formulate the desired music style.
5. Intelligent expression of music - learning of singing skills
"Tiangong SkyMusic" can also learn vibrato, opera, singing, male and female duets, automatic harmony, etc. A singing technique that allows users to create more appropriate emotional expressions in songs.
In 2023, driven by the strategy of “All in AGI and AIGC”, Kunlun Wanwei has made a lot of progress in the field of artificial intelligence, gradually forming AI large models, AI search, AI music, AI animation, AI business matrix such as AI social networking and AI games.
Currently, Kunlun Wanwei has created a comprehensive set of AI search, AI writing, AI long text reading, AI dialogue, AI speech synthesis, AI image generation, AI comic creation, AI image recognition, AI music generation, AI The "Tiangong 3.0" multi-modal "Super Model" (Super Model), which integrates multiple capabilities such as code writing and AI table generation, has become a new milestone in the AI industry.
The above is the detailed content of The fake one looks like the real thing, Tiangong Music's big model brings a subversive AI experience. For more information, please follow other related articles on the PHP Chinese website!

你可能听过以下犀利的观点:1.跟着NVIDIA的技术路线,可能永远也追不上NVIDIA的脚步。2.DSA或许有机会追赶上NVIDIA,但目前的状况是DSA濒临消亡,看不到任何希望另一方面,我们都知道现在大模型正处于风口位置,业界很多人想做大模型芯片,也有很多人想投大模型芯片。但是,大模型芯片的设计关键在哪,大带宽大内存的重要性好像大家都知道,但做出来的芯片跟NVIDIA相比,又有何不同?带着问题,本文尝试给大家一点启发。纯粹以观点为主的文章往往显得形式主义,我们可以通过一个架构的例子来说明Sam

2021年9月25日,阿里云发布了开源项目通义千问140亿参数模型Qwen-14B以及其对话模型Qwen-14B-Chat,并且可以免费商用。Qwen-14B在多个权威评测中表现出色,超过了同等规模的模型,甚至有些指标接近Llama2-70B。此前,阿里云还开源了70亿参数模型Qwen-7B,仅一个多月的时间下载量就突破了100万,成为开源社区的热门项目Qwen-14B是一款支持多种语言的高性能开源模型,相比同类模型使用了更多的高质量数据,整体训练数据超过3万亿Token,使得模型具备更强大的推

在法国巴黎举行了国际计算机视觉大会ICCV(InternationalConferenceonComputerVision)本周开幕作为全球计算机视觉领域顶级的学术会议,ICCV每两年召开一次。ICCV的热度一直以来都与CVPR不相上下,屡创新高在今天的开幕式上,ICCV官方公布了今年的论文数据:本届ICCV共有8068篇投稿,其中有2160篇被接收,录用率为26.8%,略高于上一届ICCV2021的录用率25.9%在论文主题方面,官方也公布了相关数据:多视角和传感器的3D技术热度最高在今天的开

随着智慧司法的兴起,智能化方法驱动的智能法律系统有望惠及不同群体。例如,为法律专业人员减轻文书工作,为普通民众提供法律咨询服务,为法学学生提供学习和考试辅导。由于法律知识的独特性和司法任务的多样性,此前的智慧司法研究方面主要着眼于为特定任务设计自动化算法,难以满足对司法领域提供支撑性服务的需求,离应用落地有不小的距离。而大型语言模型(LLMs)在不同的传统任务上展示出强大的能力,为智能法律系统的进一步发展带来希望。近日,复旦大学数据智能与社会计算实验室(FudanDISC)发布大语言模型驱动的中

保险行业对于社会民生和国民经济的重要性不言而喻。作为风险管理工具,保险为人民群众提供保障和福利,推动经济的稳定和可持续发展。在新的时代背景下,保险行业面临着新的机遇和挑战,需要不断创新和转型,以适应社会需求的变化和经济结构的调整近年来,中国的保险科技蓬勃发展。通过创新的商业模式和先进的技术手段,积极推动保险行业实现数字化和智能化转型。保险科技的目标是提升保险服务的便利性、个性化和智能化水平,以前所未有的速度改变传统保险业的面貌。这一发展趋势为保险行业注入了新的活力,使保险产品更贴近人民群众的实际

8月31日,文心一言首次向全社会全面开放。用户可以在应用商店下载“文心一言APP”或登录“文心一言官网”(https://yiyan.baidu.com)进行体验据报道,百度计划推出一系列经过全新重构的AI原生应用,以便让用户充分体验生成式AI的理解、生成、逻辑和记忆等四大核心能力今年3月16日,文心一言开启邀测。作为全球大厂中首个发布的生成式AI产品,文心一言的基础模型文心大模型早在2019年就在国内率先发布,近期升级的文心大模型3.5也持续在十余个国内外权威测评中位居第一。李彦宏表示,当文心

不得不说,Llama2的「二创」项目越来越硬核、有趣了。自Meta发布开源大模型Llama2以来,围绕着该模型的「二创」项目便多了起来。此前7月,特斯拉前AI总监、重回OpenAI的AndrejKarpathy利用周末时间,做了一个关于Llama2的有趣项目llama2.c,让用户在PyTorch中训练一个babyLlama2模型,然后使用近500行纯C、无任何依赖性的文件进行推理。今天,在Karpathyllama2.c项目的基础上,又有开发者创建了一个启动Llama2的演示操作系统,以及一个

杭州第19届亚运会不仅是国际顶级体育盛会,更是一场精彩绝伦的中国科技盛宴。本届亚运会中,快手StreamLake与杭州电信深度合作,联合打造智慧观赛新体验,在击剑赛事的转播中,全面应用了快手StreamLake六自由度技术,其中“子弹时间”也是首次应用于击剑项目国际顶级赛事。中国电信杭州分公司智能亚运专班组长芮杰表示,依托快手StreamLake自研的4K3D虚拟运镜视频技术和中国电信5G/全光网,通过赛场内部署的4K专业摄像机阵列实时采集的高清竞赛视频,


Hot AI Tools

Undresser.AI Undress
AI-powered app for creating realistic nude photos

AI Clothes Remover
Online AI tool for removing clothes from photos.

Undress AI Tool
Undress images for free

Clothoff.io
AI clothes remover

AI Hentai Generator
Generate AI Hentai for free.

Hot Article

Hot Tools

Zend Studio 13.0.1
Powerful PHP integrated development environment

EditPlus Chinese cracked version
Small size, syntax highlighting, does not support code prompt function

Dreamweaver Mac version
Visual web development tools

Atom editor mac version download
The most popular open source editor

mPDF
mPDF is a PHP library that can generate PDF files from UTF-8 encoded HTML. The original author, Ian Back, wrote mPDF to output PDF files "on the fly" from his website and handle different languages. It is slower than original scripts like HTML2FPDF and produces larger files when using Unicode fonts, but supports CSS styles etc. and has a lot of enhancements. Supports almost all languages, including RTL (Arabic and Hebrew) and CJK (Chinese, Japanese and Korean). Supports nested block-level elements (such as P, DIV),
