Technology peripherals
AI
Large models are popular with digital people: one sentence can be customized in 5 minutes, and you can hold it while dancing, hosting and delivering goods
Large models are popular with digital people: one sentence can be customized in 5 minutes, and you can hold it while dancing, hosting and delivering goods
You can create a 3D digital person who can work directly in as little as 5 minutes.
This is the latest shock that large models have brought to the field of digital humans.
Just like this, one sentence describes the demand:
The generated digital people can directly enter the live broadcast room and become the anchor.
It’s easy to dance in a girl group dance.
# During the entire production process, just say whatever comes to mind. The large model can automatically disassemble the requirements, and you can get designs and modify ideas instantly.
△2x speed
No longer afraid that the boss/Party A’s ideas are too novel.
Such Vincent digital human technology comes from the latest release of Baidu Intelligent Cloud. It’s time to say it or not, but it’s time to cut down the barriers to digital people’s use in one fell swoop.
After hearing about such a magical tool, we immediately secured the qualification for internal testing as usual. Let’s take a sneak peek at more details~
5 minutes per sentence, 3D digital people will be on duty directly
From Chatbot to Vincent Pictures, to Vincent Videos, it goes without saying that the changes in interaction methods brought about by large models are needless to say.
Now, on Baidu Intelligent Cloud Xi Ling platform, based on Wenxin Yiyan 4.0, digital human customization can also be realized through natural language dialogue.
For example, how many steps are needed to generate a brand spokesperson?
First, enter the prompt word "Generate a Baidu Smart Cloud brand spokesperson" and upload the logo image at the same time.
The big model will automatically start thinking step by step from multiple dimensions such as face shape, hairstyle, makeup, clothing, accessories, etc.:
Automatically create a digital person that meets the requirements.
△8x speed
If you need to adjust details, you can do it just by "speaking".
In just 5-10 minutes, a 360° high-quality digital human with no blind spots is basically formed.
After pinching the face, the next step is to attach expressions to the digital person so that he can move. It also only requires one click and wait for 1-2 minutes.
Compared with the customization cycle of high-precision 3D digital people in the past, which took several days or even months, this minute-level efficiency , it can indeed be called "subversion".
It is worth mentioning that under the premise that the efficiency has been greatly improved, the detail quality of such Vincent Digital Man still maintains a high level.
Expression details:
Action quality:
Combined with Baidu Intelligent Cloud's long-term accumulation in the field of digital people, it is easy to broadcast news and deliver goods live.
Comprehensive AI-based digital human technology
In addition to the intuitive improvement of efficiency and implementation capabilities, behind the Wensheng digital human solution launched by Baidu Intelligent Cloud this time, Many technical details are also worth talking about.
As mentioned above, its technical base is Wenxinyiyan 4.0.
The large model capabilities that play a key role include:
- Automatically dismantle the tasks and subtasks to be done
- Display the thinking process, be well-founded, and make the entire generation process "white box"
- realizes short-term memory based on content extraction, which can Continuously adjust the digital human image through dialogue
In this way, the large model becomes a digital human modeling assistant that can understand the psychology of human Party A and can imitate humans ideas, dig into every detail of digital human customization, and make the process controllable.
At the same time, the large model also demonstrates the ability to call tools behind the scenes.
For example, the "knowledge base" covering 6000 dimensions of face shape and facial features details is called to adjust the digital human face as a whole.
In addition to large model technology, Baidu Smart Cloud has also added new AI rendering technology to the Xi Ling platform, supporting AI drive and AI cloth simulation, making digital people's expressions and body movements more natural, and the texture of clothing fabrics More real. Includes:
- Dynamic wrinkle maps to make textures more realistic.
- Minute-level 4D automatic binding allows eyes, lips and other parts to be perfectly closed, and supports expression style switching.
- Real-time simulation of limb muscle extrusion and collision.
- ……
Officials also revealed that next, Baidu Intelligent Cloud plans to implement comprehensive AI for characters, behaviors, scenes, lighting, and lens elements.
Digital people, entering the era of large models and applying a new paradigm
If last year everyone was still discussing basic models in full swing, then this year Sora has Since then, the changes in application paradigms brought about by large models have become a new hot topic in the technology circle.
On top of the changes in interaction methods, what has attracted the most attention is actually efficiency improvement:
Outputting ideas and generating what is needed, large models are allowing more and more people to Many tasks that originally required a lot of time, manpower, and money have become simple, efficient, and available to everyone.
Now, the latest technological progress of Baidu Intelligent Cloud in the field of 3D digital people is a representative of the expansion of this possibility beyond the more familiar image and video fields.
It is foreseeable that more digital personnel, who were used in large enterprises and institutions in the past, are driven by the new paradigm. , it is becoming possible to enter "ordinary people's homes".
Previously, data from Tsinghua University's "Virtual Digital Human Research Report Version 2.0" showed that from the perspective of the layout of leading companies, digital human products and services for the B-side are the main component of the market, accounting for 79% .
As large model technology subverts the application model of digital humans, not only small and medium-sized enterprises no longer have to be afraid of 6-digit 3D high-precision digital humans, but C-side applications will also be expanded.
This also means that the application and commercialization of digital humans has turned a new page.
The above is the detailed content of Large models are popular with digital people: one sentence can be customized in 5 minutes, and you can hold it while dancing, hosting and delivering goods. For more information, please follow other related articles on the PHP Chinese website!
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
Notepad++7.3.1
Easy-to-use and free code editor
SublimeText3 Chinese version
Chinese version, very easy to use
Zend Studio 13.0.1
Powerful PHP integrated development environment
Dreamweaver CS6
Visual web development tools
SublimeText3 Mac version
God-level code editing software (SublimeText3)
Hot Topics
Bytedance Cutting launches SVIP super membership: 499 yuan for continuous annual subscription, providing a variety of AI functions
Jun 28, 2024 am 03:51 AM
This site reported on June 27 that Jianying is a video editing software developed by FaceMeng Technology, a subsidiary of ByteDance. It relies on the Douyin platform and basically produces short video content for users of the platform. It is compatible with iOS, Android, and Windows. , MacOS and other operating systems. Jianying officially announced the upgrade of its membership system and launched a new SVIP, which includes a variety of AI black technologies, such as intelligent translation, intelligent highlighting, intelligent packaging, digital human synthesis, etc. In terms of price, the monthly fee for clipping SVIP is 79 yuan, the annual fee is 599 yuan (note on this site: equivalent to 49.9 yuan per month), the continuous monthly subscription is 59 yuan per month, and the continuous annual subscription is 499 yuan per year (equivalent to 41.6 yuan per month) . In addition, the cut official also stated that in order to improve the user experience, those who have subscribed to the original VIP
Big model app Tencent Yuanbao is online! Hunyuan is upgraded to create an all-round AI assistant that can be carried anywhere
Jun 09, 2024 pm 10:38 PM
On May 30, Tencent announced a comprehensive upgrade of its Hunyuan model. The App "Tencent Yuanbao" based on the Hunyuan model was officially launched and can be downloaded from Apple and Android app stores. Compared with the Hunyuan applet version in the previous testing stage, Tencent Yuanbao provides core capabilities such as AI search, AI summary, and AI writing for work efficiency scenarios; for daily life scenarios, Yuanbao's gameplay is also richer and provides multiple features. AI application, and new gameplay methods such as creating personal agents are added. "Tencent does not strive to be the first to make large models." Liu Yuhong, vice president of Tencent Cloud and head of Tencent Hunyuan large model, said: "In the past year, we continued to promote the capabilities of Tencent Hunyuan large model. In the rich and massive Polish technology in business scenarios while gaining insights into users’ real needs
Context-augmented AI coding assistant using Rag and Sem-Rag
Jun 10, 2024 am 11:08 AM
Improve developer productivity, efficiency, and accuracy by incorporating retrieval-enhanced generation and semantic memory into AI coding assistants. Translated from EnhancingAICodingAssistantswithContextUsingRAGandSEM-RAG, author JanakiramMSV. While basic AI programming assistants are naturally helpful, they often fail to provide the most relevant and correct code suggestions because they rely on a general understanding of the software language and the most common patterns of writing software. The code generated by these coding assistants is suitable for solving the problems they are responsible for solving, but often does not conform to the coding standards, conventions and styles of the individual teams. This often results in suggestions that need to be modified or refined in order for the code to be accepted into the application
Seven Cool GenAI & LLM Technical Interview Questions
Jun 07, 2024 am 10:06 AM
To learn more about AIGC, please visit: 51CTOAI.x Community https://www.51cto.com/aigc/Translator|Jingyan Reviewer|Chonglou is different from the traditional question bank that can be seen everywhere on the Internet. These questions It requires thinking outside the box. Large Language Models (LLMs) are increasingly important in the fields of data science, generative artificial intelligence (GenAI), and artificial intelligence. These complex algorithms enhance human skills and drive efficiency and innovation in many industries, becoming the key for companies to remain competitive. LLM has a wide range of applications. It can be used in fields such as natural language processing, text generation, speech recognition and recommendation systems. By learning from large amounts of data, LLM is able to generate text
Can fine-tuning really allow LLM to learn new things: introducing new knowledge may make the model produce more hallucinations
Jun 11, 2024 pm 03:57 PM
Large Language Models (LLMs) are trained on huge text databases, where they acquire large amounts of real-world knowledge. This knowledge is embedded into their parameters and can then be used when needed. The knowledge of these models is "reified" at the end of training. At the end of pre-training, the model actually stops learning. Align or fine-tune the model to learn how to leverage this knowledge and respond more naturally to user questions. But sometimes model knowledge is not enough, and although the model can access external content through RAG, it is considered beneficial to adapt the model to new domains through fine-tuning. This fine-tuning is performed using input from human annotators or other LLM creations, where the model encounters additional real-world knowledge and integrates it
Advanced practice of industrial knowledge graph
Jun 13, 2024 am 11:59 AM
1. Background Introduction First, let’s introduce the development history of Yunwen Technology. Yunwen Technology Company...2023 is the period when large models are prevalent. Many companies believe that the importance of graphs has been greatly reduced after large models, and the preset information systems studied previously are no longer important. However, with the promotion of RAG and the prevalence of data governance, we have found that more efficient data governance and high-quality data are important prerequisites for improving the effectiveness of privatized large models. Therefore, more and more companies are beginning to pay attention to knowledge construction related content. This also promotes the construction and processing of knowledge to a higher level, where there are many techniques and methods that can be explored. It can be seen that the emergence of a new technology does not necessarily defeat all old technologies. It is also possible that the new technology and the old technology will be integrated with each other.
To provide a new scientific and complex question answering benchmark and evaluation system for large models, UNSW, Argonne, University of Chicago and other institutions jointly launched the SciQAG framework
Jul 25, 2024 am 06:42 AM
Editor |ScienceAI Question Answering (QA) data set plays a vital role in promoting natural language processing (NLP) research. High-quality QA data sets can not only be used to fine-tune models, but also effectively evaluate the capabilities of large language models (LLM), especially the ability to understand and reason about scientific knowledge. Although there are currently many scientific QA data sets covering medicine, chemistry, biology and other fields, these data sets still have some shortcomings. First, the data form is relatively simple, most of which are multiple-choice questions. They are easy to evaluate, but limit the model's answer selection range and cannot fully test the model's ability to answer scientific questions. In contrast, open-ended Q&A
Xiaomi Byte joins forces! A large model of Xiao Ai's access to Doubao: already installed on mobile phones and SU7
Jun 13, 2024 pm 05:11 PM
According to news on June 13, according to Byte's "Volcano Engine" public account, Xiaomi's artificial intelligence assistant "Xiao Ai" has reached a cooperation with Volcano Engine. The two parties will achieve a more intelligent AI interactive experience based on the beanbao large model. It is reported that the large-scale beanbao model created by ByteDance can efficiently process up to 120 billion text tokens and generate 30 million pieces of content every day. Xiaomi used the beanbao large model to improve the learning and reasoning capabilities of its own model and create a new "Xiao Ai Classmate", which not only more accurately grasps user needs, but also provides faster response speed and more comprehensive content services. For example, when a user asks about a complex scientific concept, &ldq
