Alibaba Unveils Qwen VLo: Advanced AI Image Generation and Editing Service

Alibaba Unveils Latest AI Service for Images in Push for Users

Alibaba Group Holding Ltd. unveiled a new iteration of its artificial-intelligence technology that will make it easier for users to generate and modify images from texts and visuals, as the Chinese e-commerce giant continues its aggressive push into AI. The Hangzhou-based company introduced Qwen VLo, part of a series of AI services under the company's Qwen brand. The new model is an upgrade from Qwen2.5-VL and is now able to generate text-to-image and image-to-image results. It also has a technology called progressive generation, meaning users can see the process as an image is created.

Alibaba unveils latest AI service for images in push for users - The Economic Times

The Hangzhou-based company introduced Qwen VLo, part of a series of AI services under the company's Qwen brand. The new model is an upgrade from Qwen2.5-VL and is now able to generate text-to-image and image-to-image results. It also has a technology called progressive generation, meaning users can see the process as an image is created.Alibaba Group Holding Ltd. unveiled a new iteration of its artificial-intelligence technology that will make it easier for users to generate and modify images from texts and visuals, as the Chinese ecommerce giant continues its aggressive push into AI. The Hangzhou-based company introduced Qwen VLo, part of a series of AI services under the company's Qwen brand. The new model is an upgrade from Qwen2.5-VL and is now able to generate text-to-image and image-to-image results. It also has a technology called progressive generation, meaning users can see the process as an image is created. "This newly upgraded model not only 'understands' the world but also generates high-quality recreations based on that understanding," the company said in a blog post. "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." Best known for its ecommerce operations in China, Alibaba has been charging into AI and building standalone offerings around Qwen. In February, Chief Executive Officer Eddie Wu went so far as to say the company's "primary objective" is now artificial general intelligence, a goal in the industry to build AI systems with human-level intellectual capabilities. With the new Qwen multimodal model, it's aiming to compete with a flurry of new visual interfaces in the market, including from OpenAI. It also faces aggressive domestic competition from the likes of DeepSeek. After DeepSeek stunned the industry with a powerful model it said took just a few million dollars to build, China's technology leaders flooded the market with a rapid succession of low-cost AI services. Alibaba has rapidly updated its Qwen series, adding new capabilities to process text, pictures, audio and video -- with the efficiency to run directly on phones and laptops. It unveiled a new version of its AI assistant Quark app in March.

Alibaba launches Qwen VLo AI image generator to compete globally By Investing.com

Investing.com -- Alibaba Group Holdings Ltd ADR (NYSE:BABA) unveiled its new multimodal AI model Qwen VLo on Friday, designed to generate and edit high-quality visuals from text and image prompts. The new "AI creative engine" represents China's latest entry in the rapidly advancing global AI race, following OpenAI's addition of image generation to ChatGPT in March and Google's (NASDAQ:GOOGL) release of Imagen 4 in May. Qwen VLo allows users to create complex scenes step-by-step, make on-the-fly edits, and generate images in multiple languages through plain-language instructions. "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," Alibaba wrote in its launch announcement. The model combines dynamic resolution training with progressive generation that refines outputs from left-to-right and top-to-bottom. Key features include artistic style transfers, realistic object modifications, and poster creation - functions aimed at designers, marketers, and educators. According to Alibaba, Qwen VLo can process complex visual editing commands in a single instruction while maintaining semantic accuracy. When users input images and request modifications like color changes or style adjustments, the model preserves core structure and context fidelity. The system supports multiple languages, particularly Chinese and English, to serve a global user base and make the technology more accessible to non-technical creators. Alibaba's international push comes as Beijing seeks to accelerate domestic AI development, especially as Chinese firms face increasing restrictions on access to U.S.-built chips and foundational models. The company acknowledged that Qwen VLo remains in preview with known limitations including inconsistencies and occasional instruction compliance failures. "We will continue to iterate and improve the stability and robustness of the model," Alibaba stated. Users can currently access this preview version through Qwen Chat.