Alibaba releases image generating AI model

Alibaba Group (NYSE:BABA) has released an image generating artificial intelligence model, Qwen VLo, which will compete with other image generators such as OpenAI’s 4o and Google’s (GOOG)(GOOGL) Imagen 4.

The Hangzhou, China-based e-commerce giant also provides cloud services and continues to build on its AI offerings. It is currently working with Apple (AAPL) to bring Apple Intelligence to the mainland.

“This newly upgraded model not only ‘understands’ the world but also generates high-quality recreations based on that understanding, truly bridging the gap between perception and creation,” said the Qwen team in a blog post. “Note that this is a preview version and you can access it through Qwen Chat. You can directly send a prompt like ‘Generate a picture of a cute cat’ to generate an image or upload an image of a cat and ask ‘Add a cap on the cat’s head’ to modify an image.”

The model is intended to have more precise content understanding and support for open-ended instruction-based editing. It can understand English and Chinese.

“Qwen VLo is capable of directly generating images and modifying them by replacing backgrounds, adding subjects, performing style transfers, and even executing extensive modifications based on open-ended instructions, as well as handling detection and segmentation tasks,” the company said.