Alibaba Cloud, the digital technology and intelligence backbone of China’s Alibaba Group, has launched Tongyi Wanxiang, a text-based AI image generator similar to DALL-E, Midjourney and Stable Diffusion. The tool is current available to enterprise customers in China for beta testing.
Tongyi Wanxiang was developed using Composera large model courtesy of Alibaba Cloud that allows greater control over the final image output, such as spatial layout and palettes, while retaining the quality and creativity of image synthesis.
Tongyi Wanxiang: Text-To-Image in Chinese and English
Tongyi Wanxiang uses a generative AI model that responds to requests for text in Chinese and English to generate detailed drawings in a variety of styles, including watercolor, Chinese and oil painting, animation, sketch, flat illustration, and 3D cartoon. This model can also transform any image into a new image with a similar style and change image styles via style transfer, which retains the original image content while applying the visual style of another image.
Alibaba has launched Tongyi Wanxiang, an AI tool that translates text prompts into images in different styles. It is available for beta testing by the company’s customers in China.@AlibabaGroup @alibaba_cloud pic.twitter.com/TPcJbxKLX3
— She’s Better (@SheIsBetterSg) July 11, 2023
This model leverages Alibaba Cloud’s knowledge management, visual AI, and natural language processing capabilities. It uses multilingual materials for enhanced training, resulting in the creation of more contextually accurate and relevant images. By optimizing the high-resolution diffusion process based on signal-to-noise ratio, this model is able to balance compositional accuracy and detail sharpness, resulting in visually stunning high-contrast images against clean backgrounds.
“Tongyi Wanxiang is another significant milestone in our pursuit of advanced generative AI models as we continue to explore paradigm-shifting technologies that empower 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 imagery will become more accessible, facilitating the development of innovative AI arts and creative expression for businesses in various sectors, including e-commerce, games, design, and advertising.
ModelScopeGPT: Versatile Framework for Complex AI Tasks
Apart from Tongyi Wanxiang, Alibaba Cloud also announced the launch ModelScopeGPT, a versatile framework designed to assist users in solving complex and specialized AI tasks across the language, vision, and speech domains by leveraging the various AI models on ModelScope. ModelScope is an open source Model-as-a-Service (MaaS) platform introduced by Alibaba Cloud last year, featuring more than 900 AI models.
LLM Development at Alibaba
Alibaba Cloud launched a Large Language Model (LLM) named Tongyi Qianwen in April, and plans to integrate LLM across Alibaba’s businesses to improve user experience in the near future. Since the model’s launch, more than 300,000 requests for beta testing have been received from companies from various sectors, including fintech, electronics, transportation, fashion, and dairy.
Tongyi Qianwen has also been integrated into the intelligent Alibaba Cloud assistant device, tingwu, enabling assistants to understand and analyze multimedia content with a high degree of accuracy and efficiency. More than 360,000 users have accessed the AI-powered assistant since launch.
Thus the article about Alibaba Launches AI Image Generator Similar to DALL-E, Midjourney, Stable Diffusion
I hope the information in the article is useful to you. Thank you for taking the time to visit this blog. If there are suggestions and criticisms, please contact us : firstname.lastname@example.org