-
Ali Tongyi will release a big model of AI video generation, supporting text-born video and graph-born video
Ali Tongyi will release a big model of video generation during the 2024 Yunqi Conference (September 19th to September 21st). At present, Tongyi App channel and PC terminal of Tongyi Wanxiang have on-line "Video Generation" portal, which only supports users to make reservation, but is not open for use. The content of the page shows that the newly released video generation model is independently researched and developed by Tongyi Labs, and contains two creation modes: "text-generated video" and "map-generated video". After successful reservation, Ali Tongyi will notify users when they are qualified to use it, and give them 66 inspiration values (valid for 30 days). ...- 3.1k
-
Ali Tongyi opens the Olympic AI model for free: supports Chinese-French translation and has Olympic knowledge
Alibaba's Alitongyi announced on July 31 that it will open its AI big model designed for the Olympics for free. The model not only has professional knowledge in the Olympic field, but also integrates Chinese-French translation functions. Users can use this service for free through the Tongyi APP. The AI big model has been specially trained for the Olympics and can quickly answer various questions related to the Olympics. Whether it is event knowledge or athletes from various countries and event history, users only need to ask simple questions to get detailed and professional answers. During the viewing process, if you encounter problems with the rules of the event, AI can provide detailed answers. In addition, users can also take pictures...- 1.6k
-
Alibaba Tongyi's audio generation model FunAudioLLM is open source and supports scenarios such as emotional voice dialogue and audiobooks
Ali Tongyi Labs recently open-sourced an audio generation large model project called FunAudioLLM, which aims to enhance the natural speech interaction experience between humans and large language models (LLMs). The project consists of two core models: SenseVoice and CosyVoice. CosyVoice focuses on natural speech generation with multi-language support, timbre and emotion control, and excels in multi-language speech generation, zero-sample speech generation, cross-language sound synthesis and command execution. It is trained with 150,000 hours of data and supports five languages, Chinese, English, Japanese, Cantonese and Korean...- 8.5k
❯
Search
Scan to open current page
Top
Checking in, please wait
Click for today's check-in bonus!
You have earned {{mission.data.mission.credit}} points today!
My Coupons
-
¥CouponsLimitation of useExpired and UnavailableLimitation of use
before
Limitation of usePermanently validCoupon ID:×Available for the following products: Available for the following products categories: Unrestricted use:Available for all products and product types
No coupons available!
Unverify
Daily tasks completed: