Author: IBL News

IBL News | New York

Chinese company Alibaba Cloud, creator of the AI models Qwen, released its advanced image model this month as open-source software, unifying text-to-image generation and image editing into a single model.

Qwen-Image-2.1 includes a 7B-parameter visual generation component and native support for generating and editing transparent images.

Specifically, it generates regular or transparent images from prompts, edits transparent layers, and extracts subjects from photos (as shown below).

According to the company, “Despite its compact size, the model delivers strong image generation quality, and the Qwen-Image-Bench comparison below shows its performance alongside other open-source and closed-source models.”

• “Use up to 10 reference images, specify local edits, preserve people and products, and handle a wide range of tasks.”

• “Realistic textures and refined aesthetics: Improved typography, portrait lighting, and fine details make generated images more visually compelling.” 

• Examples of pictures generated with Qwen-Image-2.1

IBL News | New York

SpaceXAI released Grok 4.7, its most advanced model for coding and knowledge work, and according to the company, it is “highly competitive in its class.”

It has been released at the same price and speed as Grok 4.6.

However, Grok 4.7 uses a new, larger base model compared to Grok 4.6.

SpaceX explained that “it was trained with a longer reinforcement learning run on a harder mix of tasks, weighted toward problems that take many hours to complete.”

On CursorBench 4.0, which stresses longer-running coding tasks, Grok 4.7 is at the frontier in price-performance.