In April, Open AI released upgraded image generation technology with Chat GPT Images 2. Five months later, the company is releasing an enhanced version, Chat GPT Images 2.5.

Chat GPT Images 2 was a notable leap over the company’s earlier image generation tools. It added 2K resolution output, multiple aspect ratio support, and the ability to use web research for up-to-date information. Images 2 also added non-Latin language expertise and two intelligence levels: Instant and Thinking. The latest Images 2.5 version touts “sharper details, faster generation, more precise editing, and better tools for creating and sharing.”

“Images 2.5 produces more natural lighting and richer textures, is better at preserving the subjects in your reference photos, and follows editing instructions more reliably across multiple turns,” Open AI says. “We’ve also reduced image generation latency by up to 50% compared with Images 2.0, so you can generate images and refine your concepts more quickly.”

Additionally, the company details a new “Sketch” feature that enables drawing directly in Chat GPT. This can be used as a reference for image generation. Plus Open AI is introducing templates for popular image formats, prompt sharing for others to try your ideas related to image-gen, and more. Additionally, Open AI is releasing two versions of Images 2.5 for developers to build around in their apps: GPT-Image-2.5 Flare and GPT-Image-2.5 Sunburst, available through Open AI’s API. Images 2.5 is rolling out today to Chat GPT, Chat GPT Work, and Codex users across all tiers on desktop, mobile, and web.