Alibaba Cloud Tongyi WanxiangNews

Alibaba Cloud unveils AI image generation model

As more technology companies discover the potential of generative artificial intelligence (AI), Alibaba Cloud recently unveiled its latest AI image generation model called Tongyi Wanxiang.

Alibaba Cloud, the digital technology and intelligence backbone of Alibaba Group, made the generative AI model now available for enterprise customers in China for beta testing. Wanxiang means tens of thousands of images.

“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,” said Jingren Zhou, CTO of Alibaba Cloud Intelligence.

Alibaba Cloud unveils new language AI model
Alibaba Cloud opens partnership program for use of AI language model

Powered by Alibaba Cloud’s 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.

Image generation

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.

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 watercolors, oil and Chinese painting animation, sketch, flat illustration, and 3D cartoons. 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.

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.

1 reply »