OpenAI Rolls Out ChatGPT Images 2.5 With Sketch Editing
OpenAI says the update adds doodle-based prompts, in-image comments and up to 50% faster image generation.
- On Tuesday, OpenAI announced ChatGPT Images 2.5, introducing a new Sketch feature that allows users to generate images by drawing doodles directly inside the ChatGPT interface.
- This update is rolling out to ChatGPT, ChatGPT Work, and Codex users across all tiers on desktop, mobile, and web, providing broad platform access.
- Users can activate the drawing tool by typing "@Sketch" into the chat box, while new commenting capabilities allow for precise modifications by selecting specific image parts.
- OpenAI reports that ChatGPT Images provides "more natural lighting and richer textures," improves instruction following "across multiple turns," and reduces latency by "up to 50%" versus previous versions.
- By combining freehand input with iterative editing controls, these updates streamline the creative process, enabling more intuitive image generation for all supported ChatGPT user tiers.
98 Articles
98 Articles
GPT Images 2.5 promises edits that leave the rest of your image alone
When OpenAI launched GPT Images 2.5 this week, the company promised better results for a common editing task: changing one part of an image without messing up the rest. And so developers have two new models to try, Flare and Sunburst, but some homework awaits anyone choosing between them. OpenAI lists identical token rates for both, without explaining how their per-image costs compare. Flare is positioned as the faster, “default” option for most…
OpenAye launched a new version of the ChatGPT image-generation and editing tool, called "Images 2.5," with improvements in the quality and speed of image generation and the accuracy of the implementation of user modifications.
OpenAI has launched ChatGPT Images 2.5, the new version of its image generator inside ChatGPT, which replaces Images 2.0. It comes with improvements focused on three fronts, speed, editing accuracy and tools to give visual instructions without relying only on text. The update is already active on all levels ... Continue reading "ChatGPT Images 2.5, the update that lets you draw a sketch and edit just what you point out"
ChatGPT Adds Images 2.5 Model, New Feature Turns Doodles Into AI Photos
The new model drops image-generation latency by 50% and is better at adding natural light and rich text, OpenAI claims. Months after updating ChatGPT’s image generation with Images 2.0, OpenAI on Tuesday released an upgraded model and a new Sketch tool that turns your doodles into high-quality AI-generated imagery.Images 2.5 is currently rolling out to all ChatGPT users on desktop, mobile, and web. Compared with …
ChatGPT Images 2.5 offers precise control, greater graphic fidelity and production speed
OpenAI's ChatGPT Images 2.5 Sharpens the Picture for Creators and Enterprises
OpenAI launched ChatGPT Images 2.5 with 50% faster generation, superior subject preservation, precise comment-based editing, and a new Sketch tool that turns rough drawings into polished images. The update strengthens the model's role in professional creative pipelines while maintaining safety through metadata and watermarks. It builds directly on the reasoning capabilities introduced earlier this year.
Coverage Details
Bias Distribution
- 40% of the sources are Center
Factuality
To view factuality data please Upgrade to Premium
