Alibaba Cloud, the digital technology and intelligence backbone of Alibaba Group, today unveiled its latest AI image generation model, Tongyi Wanxiang (‘Wanxiang’ means ‘tens of thousands of images’) at the World Artificial Intelligence Conference 2023. The cutting-edge generative AI model is now available for enterprise customers in China for beta testing.
In addition, the cloud pioneer 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.
“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.”
Introducing Tongyi Wanxiang for Image Generation
The generative AI model is adept at handling various tasks, responding to text prompts in Chinese and English to generate detailed images in an array of styles, encompassing watercolours, oil and Chinese painting to animation, sketch, flat illustration, and 3D cartoons. Moreover, the model can 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.
Powered by Alibaba Cloud’s trailblazing technologies in knowledge arrangement, visual AI and natural language processing (NLP), the model leverages multilingual materials for enhanced training. It boasts a robust semantic comprehension capability, resulting in more accurate and contextually relevant image generation.
Additionally, by optimizing the high-resolution diffusion process based on the signal-to-noise ratio, the model can strike a balance between composition accuracy and detail sharpness while enhancing its ability to generate high-contrast, visually stunning images with clean backgrounds.
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.
Text-to-image generation examples by Tongyi Wanxiang:
Prompt:
Picture a cityscape at twilight, a world merging modern architecture with the evocative aesthetics of anime.
Prompt:
Immersive, captivating, grayscale coloring, featuring a tiger in the tranquil mandala forest. The image is composed of lines and brushstrokes.
Demo video of Tongyi Wanxiang
Take a look at how Alibaba Cloud’s generative AI model Tongyi Wanxiang creates images. In this video, we show how the generative AI model, whose name means ‘tens of thousands of images’ in Mandarin, is adept at handling a wide range of tasks.
Tongyi Wanxiang responds to text prompts in Mandarin and English to generate detailed images in an array of mediums and styles from watercolors, oils and Chinese paintings to animation, sketches, and 3D cartoons.
Source: Alibaba Cloud, July 7, 2023