Alibaba Cloud, the digital technology and intelligence backbone of the Chinese Alibaba Group, has launched Tongyi Wanxiang, a text based AI image generator similar to DALL-E, Midjourney and Stable Diffusion. The tool is currently available for enterprise customers in China for beta testing.
Tongyi Wanxiang was developed using Composer, Alibaba Cloud's proprietary large model that enables greater control over the final image output, such as spatial layout and palette, while maintaining image synthesis quality and creativity.
Tongyi Wanxiang: Text-To-Image in Chinese and English
Tongyi Wanxiang uses a generative AI model that responds to text prompts in both Chinese and English to generate detailed images in a variety of styles, including watercolors, oil and Chinese painting, animation, sketch, flat illustration, and 3D cartoons. The model can also transform any image into a new one with a similar style and stylize images through style transfer, which preserves the content of the original image while applying the visual style of another picture.
Alibaba has launched Tongyi Wanxiang, an AI tool that translates text prompts into images in different styles. It's available for beta testing by enterprise customers in China.@AlibabaGroup @alibaba_cloud pic.twitter.com/TPcJbxKLX3
— She is Better (@SheIsBetterSg) July 11, 2023
The model leverages Alibaba Cloud's knowledge arrangement, visual AI, and natural language processing capabilities. It uses multilingual materials for enhanced training, resulting in more accurate and contextually relevant image generation. By optimizing the high-resolution diffusion process based on the signal-to-noise ratio, the model can balance composition accuracy and detail sharpness, generating high-contrast, visually stunning images with clean backgrounds.
“Tongyi Wanxiang represents 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 art and creative expressions for businesses across a wide range of sectors, including e-commerce, gaming, design, and advertising.
ModelScopeGPT: A Versatile Framework for Complex AI Tasks
In addition to Tongyi Wanxiang, Alibaba Cloud also announced the launch of ModelScopeGPT, a versatile framework designed to assist users in accomplishing complex and specialized AI tasks across language, vision, 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.
LLM-Development at Alibaba
Alibaba Cloud launched its Large Language Model (LLM) named Tongyi Qianwen in April, and it plans to integrate the LLM across Alibaba's various businesses to improve the user experience in the near future. Since the model's launch, over 300,000 beta testing requests were received from enterprises from a broad range of sectors, including fintech, electronics, transport, fashion, and dairy.
Tongyi Qianwen has also been integrated into Alibaba Cloud's intelligent assistant, Tingwu, enabling the assistant to comprehend and analyze multimedia content with high levels of accuracy and efficiency. Over 360,000 users have accessed the AI-powered assistant since its launch.