Alibaba Cloud, the digital technology and intelligence backbone of Alibaba Group, has unveiled its latest AI image generation model, Tongyi Wanxiang (Wanxiang means tens of thousands of images).
The state-of-the-art generative AI model is now available to enterprise customers in China for beta testing.
Additionally, the cloud pioneer announced the launch of ModelScopeGPT, a versatile framework designed to assist users in performing complex and specialized AI tasks in language, visual, and speech domains by leveraging various AI models on ModelScope. ModelScope is an open source Model-as-a-Service (MaaS) platform introduced by Alibaba Cloud last year, featuring over 900 AI models.
Tongyi Wanxiang represents another significant milestone in our pursuit of advanced generative AI models as we continue to explore paradigm-shifting technologies that enable businesses and communities to unleash greater creativity and productivity, said Jingren Zhou, CTO of Alibaba Cloud Intelligence .
With the release of Tongyi Wanxiang, high-quality generative AI images will become more accessible, facilitating the development of innovative AI art and creative expressions for companies across a wide range of industries, including e-commerce, games, design, and advertising .
Introducing Tongyi Wanxiang for image generation
The generative AI model is adept at handling various tasks, responding to text requests in Chinese and English to generate detailed images in a range of styles, including watercolor, oil and Chinese painting, animation, sketch, flat illustration, and cartoon animated 3D. Additionally, the template can transform any image into a new one with a similar style and stylize images through style transfer, which preserves the original image content while applying the visual style of another image.
Powered by Alibaba Clouds cutting-edge technologies in knowledge organization, visual artificial intelligence, and natural language processing (NLP), the model leverages multilingual materials for advanced training. It boasts robust semantic understanding, which results in more accurate and contextually relevant image generation.
Furthermore, by optimizing the high-resolution scattering process based on signal-to-noise ratio, the model can strike a balance between compositional accuracy and sharpness of detail, while enhancing its ability to generate visually stunning, high-contrast images with clean backgrounds. .
Tongyi Wanxiang was developed using Composer, Alibaba Clouds proprietary large format template that allows for more control over the final image output, such as spatial layout and palette, while maintaining the quality and creativity of the image synthesis .
Examples of text-to-image generation by Tongyi Wanxiang:
Imagine a twilight cityscape, a world that blends modern architecture with evocative anime aesthetics.
Beautiful nature superimposed into an infinity loop sign with vibrant colors.
Immersive, captivating, grayscale coloring with a tiger in the peaceful mandala forest. The picture is made up of lines and brush strokes.
A six-year-old girl’s beautiful and exquisite Chinese-style Hanfu is displayed in front of a coat rack, medium close-up, 85mm lens.
ModelScopeGPT launched for sophisticated AI tasks
Alibaba Cloud also unveiled ModelScopeGPT, a powerful framework designed to leverage the power of Large Language Models (LLMs) available on the platform. ModelScopeGPT will use the LLMs as a controller to connect a wide range of domain-specific expert models into the ModelScope open source community. Built within the rich Model-as-a-Service ecosystem, ModelScopeGPT leverages the various AI features offered on the Alibaba Cloud. Enterprises and developers can leverage ModelScopeGPT for free to access and run the most suitable models to perform sophisticated AI tasks based on user requests, such as multilingual video development.
Alibaba Cloud launched its LLM named Tongyi Qianwen in April and plans to integrate the LLM into Alibaba’s various businesses in order to improve the user experience in the near future. The company’s customers and developers will also have access to the template to cost-effectively build custom AI capabilities. Since the launch of the models, over 300,000 beta test requests have been received from companies across a wide range of industries, including fintech, electronics, transportation, fashion and dairy.
Tongyi Qianwen has also been integrated into Alibaba Clouds intelligent assistant, Tingwu, enabling the assistant to understand and analyze multimedia content with high levels of accuracy and efficiency. Over 360,000 users have accessed the AI-powered assistant since its launch.
AI Hackathon Competition to inspire innovation
ModelScope also hosted its first AI Hackathon in China to facilitate industrial applications of AI models, with cash prizes and funding opportunities from leading venture capital firms as incentives.
Of the more than 300 participating teams, 56 made it to the finals. Participants competed for first prize on two tracks. One is to innovate on a large language model to solve a real-life problem. The second is to leverage existing pre-trained models to complete an assigned task, such as text-to-image generation, or to build an LLM-based standalone agent to use the right models for specific tasks.
By hosting contests and other community events, we want to engage more developers and entrepreneurs and encourage them to bring their ideas to life, unlock productivity, and create more versatile AI tools that transform and shape the future of our industries, Zhou said.
Want to learn more about cyber and cloud security from industry leaders? Check out Cyber Security & Cloud Expo taking place in Amsterdam, California and London. Explore more upcoming corporate technology events and webinars brought to you by TechForge here.
#Alibaba #Cloud #launches #image #generation #model #Tongyi #Wanxiang
Image Source : www.cloudcomputing-news.net