xAI has released Imagine Image 2.0, a new image generation model that lands second behind OpenAI's GPT-Image-2 in public benchmark rankings. The model arrives as a new "Quality Mode" on grok.com/imagine and inside Grok's iOS and Android apps. API access is coming soon, according to xAI.
The launch puts xAI in a tight race with OpenAI. On the Arena leaderboards as of August 7, 2026, the faster "low" variant of Imagine Image 2.0 takes second place globally in both the Image Edit and Text-to-Image categories. OpenAI's GPT-Image-2 leads both lists.
Arena Scores Show a Narrow Gap
The numbers tell a close contest. In the Image Edit Arena, the "low" variant of Imagine Image 2.0 scores an Elo rating of 1,439. OpenAI's GPT-Image-2 reaches 1,463 in the same arena. The margin is 24 points.
The Text-to-Image Arena shows a similar pattern. Imagine Image 2.0's "low" variant hits 1,320, while GPT-Image-2 scores 1,380. That gap sits at 60 points.
Further down the rankings sit Reve 2.1, Meta's Muse-Image, Alibaba's Qwen-Image-3.0-Pro, Google's Gemini, and ByteDance's SeedDream. The new xAI model also beats the "Quality" variant of its predecessor by a wide margin in these tests, according to the leaderboard data.
Built for Precision and Consistency
xAI says Imagine 2.0 is designed to follow instructions with fine-grained accuracy. The company claims it keeps typography and layout clean in complex visuals. It also aims to stay consistent across multiple generations, a feature that matters for design work and brand assets.
The model ships with several editing features. A tool called "Magic Wand" modifies only the selected area of an image, according to xAI. A segmentation feature lets users pick precise regions. A background removal tool exports subjects with a transparent background.
Stay ahead of the AI curve
The most important updates, news, and content — delivered weekly.
No spam. Unsubscribe anytime.
Multi-Ref Editing allows users to combine up to five input images into a single generation. "Smart Resize" converts an existing image to any aspect ratio, with the model filling in the extra space on its own. These tools are built for iterative workflows, the company said.
Templates for Common Workflows
xAI is adding templates that bundle common image workflows into preconfigured starting points. Template categories span photo editing, product photography, marketing materials, design tools, game assets, and streaming emojis. The templates aim to reduce setup time for repetitive tasks.
The company is also showing a feature that generates characters, locations, and props separately while keeping the visual style consistent across all images. This positions Imagine 2.0 as a planning tool for larger projects.
A Step Toward Video Production
xAI frames the consistent visual worlds feature as a stepping stone toward full video production workflows. Imagine 2.0 can generate consistent visual worlds with characters, props, and locations that serve as a starting point for video production, xAI says. The company included an image illustrating this capability.
That direction hints at where xAI wants to take its creative tools next. For now, the model is available to users through Grok's apps and the web interface, with API access expected to follow.