ChatGPT Images 2.5 Launches With Sketch Tool That Transforms Doodles Into Polished AI Images
16 Sources
[1]
You can doodle in ChatGPT now, and it'll transform your drawings into polished images - how to try it - ZDNET
Lance Whitney is a freelance technology writer and trainer with a background in IT.... Read full bio * ChatGPT's Sketch tool can turn your rough drawings into polished images. * Just draw your sketch in ChatGPT and submit it to the AI for transformation. * You can edit and share the generated
[2]
ChatGPT Sketch turns your bad drawings into detailed AI images
OpenAI announced ChatGPT Images 2.5 on Tuesday and is adding a new way to tell ChatGPT what you want it to make an image of: by drawing a doodle. With a new feature called Sketch, you can just draw something right inside ChatGPT and then tell ChatGPT how you want it to make an image based on that
[3]
ChatGPT Adds Images 2.5 Model, New Feature Turns Doodles Into AI Photos
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
[4]
ChatGPT Sketch turns your paint-like doodles into beautifully rendered images
* ChatGPT Images 2.5 lands: faster generation, more realistic images, and stronger edit capabilities. * Sketch turns rough doodles into finished images -- sketch a layout, style, or outfit and let AI refine it. * The feature is widely available -- type '@sketch' in ChatGPT to start doodling and
[5]
ChatGPT Images 2.5 can generate and edit your AI slop poster with more accuracy
ChatGPT Images 2.5 is also better at editing over multiple steps without degrading quality. People have been creating and editing images with ChatGPT for a long time. So much so, in fact, that they've occasionally stumbled upon absolutely bizarre generations. However, OpenAI is now making it
[6]
OpenAI's image models are now inside Adobe's Firefly
OpenAI released ChatGPT Images 2.5 with two new API models, one of which Adobe has already put into Firefly. The company says more than 3 billion images a week are created across ChatGPT and its image API. The notable additions are interface features rather than model research, including the
[7]
I Turned Jordan Drake Into a Knight Using ChatGPT's New Image Model
ChatGPT has updated its image generator, which promises to be more faithful to source photos. When someone uploads a photo into ChatGPT and asks it to make edits, what many people don't realize is that the AI chatbot is using that photo in much the same way it uses text as a prompt. This means
[8]
ChatGPT Images gets better at faces, pets and edits
Why it matters: For all their capabilities, AI image generators have struggled in the past to keep people and pets looking like themselves and editing tools have been limited. The big picture: The updated image engine within ChatGPT is not only faster than its predecessor, but does a much better
[9]
ChatGPT Images 2.5 lets you sketch what you want instead of trying to describe it
OpenAI is rolling out ChatGPT Images 2.5, its newest image generation model, and it brings a solid mix of speed and quality upgrades that should make your AI art sessions a lot less frustrating. People are already generating over 3 billion images every week across ChatGPT and the API, and this
[10]
OpenAI Just Launched ChatGPT Images 2.5, and Here's How It Compares to Google's Nano Banana 2
In among the maelstrom of everything else that's happening with AI right now, OpenAI has pushed out ChatGPT Images 2.5, which it describes as faster, sharper, and smarter, with "better tools for creating whatever you can dream of." Those new tools include templates, more precise editing features,
[11]
ChatGPT Images 2.5: What's new in OpenAI's latest image model
OpenAI has launched ChatGPT Images 2.5, offering users greater control over image creation and editing. This new model provides sharper details and more natural lighting, enhancing realism significantly. Users can now preserve reference image features better while making desired modifications. The
[12]
ChatGPT Images 2.5 Turns Rough Sketches Into Final Art
ChatGPT Images 2.5 brings updates that improve the speed and quality of AI-generated visuals, offering new ways to approach creative projects. Paul Lipsky highlights the sketch-based image creation feature, which allows users to begin with a simple outline or concept sketch. The AI then refines
[13]
ChatGPT Images 2.5: Sketch, New Features, Editing Improvements
Faster generation: ChatGPT Images 2.5 cuts image-generation latency by up to 50% compared with Images 2.0, according to OpenAI. Sketch and editing: The new Sketch feature turns rough drawings into finished images, while comments allow users to target specific areas for changes. Two API models:
[14]
OpenAI launches ChatGPT Images 2.5 with faster generation By Investing.com
Investing.com -- OpenAI released ChatGPT Images 2.5 on Tuesday, introducing improvements to image quality, editing precision, and generation speed for its image creation tools. The company said users generate more than 3 billion images weekly across ChatGPT Images and GPT-Image models in the API.
[15]
ChatGPT Images 2.5: OpenAI Boosts Editing Control With Sketch
OpenAI launched ChatGPT Images 2.5 on September 8, 2026, bringing a faster image engine and stronger editing tools to ChatGPT. The update rolled out to ChatGPT, ChatGPT Work, and Codex users across desktop, mobile, and web on all tiers. OpenAI shared the news first with Axios, and the company
[16]
OpenAI launches ChatGPT Images 2.5 with faster generation, better editing and new Sketch feature
The new model is said to offer sharper details, more natural lighting and richer textures while preserving people and subjects from reference images. OpenAI has officially introduced the ChatGPT Images 2.5, its latest image generation model. It brings improved quality, faster generation and more
Share
Copy Link
OpenAI released ChatGPT Images 2.5 with a revolutionary Sketch feature that turns rough drawings into professional AI images. The upgraded AI image generation model delivers 50% faster performance, enhanced natural lighting, and improved multi-step editing capabilities for all ChatGPT users.
OpenAI Unveils ChatGPT Images 2.5 With Enhanced Performance
OpenAI has released ChatGPT Images 2.5, its latest AI image generation model that delivers substantial improvements in speed and quality. The upgraded model reduces image generation latency by up to 50% compared with Images 2.0, making it significantly faster at producing AI images
1
3
. According to OpenAI, ChatGPT Images 2.5 creates visuals with more natural lighting and richer textures while better preserving subjects from reference photos2
. The model is rolling out to all ChatGPT, ChatGPT Work, and Codex users across desktop, mobile, and web platforms5
.ChatGPT Sketch Transforms Doodles Into Professional AI Photos
The standout feature of this release is ChatGPT Sketch, an AI-driven creative tool that converts user doodles into detailed AI-generated images. Users can activate the feature by typing @Sketch into the chat box, which opens a drawing window with various pencils and colors
1
. The tool allows anyone to draw rough sketches directly in ChatGPT and transform your drawings into polished images through simple text instructions4
. Early testing demonstrates impressive results—one user's crude mouse-drawn cat doodle was successfully converted into a realistic photo2
. Another tester found that ChatGPT interpreted their rough sketch of a person wearing a hat as a turkey in a Pilgrim hat, showcasing the AI's creative interpretation capabilities1
.Advanced Editing Capabilities Enhance User Experience
ChatGPT Images 2.5 introduces improved editing capabilities that maintain consistency across multiple iterations. The model is better at following edit instructions across multiple turns without degrading image quality or altering earlier changes
5
. Users can now leave comments directly on specific parts of images for precise edits—one tester used this feature to change a cat's eyes from blue to green2
. The model can precisely edit single elements in photos, allowing users to change backgrounds without altering subjects or modify text while keeping the rest intact5
. Additional tools include the ability to mark up images, erase unwanted parts, remove backgrounds, and resize outputs1
.Related Stories
Templates Streamline Creative Workflows
OpenAI has integrated built-in templates to accelerate creative workflows and improve the user experience. Instead of starting from scratch, users can access pre-set formats through Images > Templates, including options like Poster, Merch, bobblehead, statue, anime, sticker, and icon
3
1
. These templates not only provide specific visual styles but also add descriptions to flesh out the image and scene context1
. The templates help users quickly sketch layouts for rooms, concept outfits, or create funny doodles that ChatGPT then refines into complete images4
. Users can download finished images as PNG files, copy links, or share directly on social media1
.Implications For Content Creation and Design
The release arrives days after OpenAI introduced GPT-6 Astra and positions ChatGPT Images 2.5 as a significant advancement in faster image generation technology
3
. The model's improved visual intelligence can understand complex instructions and real-world information to generate better AI images5
. It can also create images with transparent backgrounds, beneficial for sticker creation and design work5
. While the tool democratizes image creation for users without artistic skills, observers note that the prompt paired with sketches does much of the heavy lifting in determining final outputs3
. The accessibility of these tools raises questions about the volume of AI-generated content that may flood social media platforms in coming weeks5
.References
Summarized by
Navi
[5]
Related Stories
Recent Highlights
1
OpenAI Pauses AI Model Training After Agent Hacks Australian Government Website
Technology
2
Bill Gates Warns AI Could Cause a Billion Deaths, Calls for Urgent Federal Regulation
Policy and Regulation
3
Meta Unveils Camera-Free AI Glasses and Muse Integration Amid Privacy Debate at Connect 2026
Technology
Recent Highlights
Today's Top Stories
Don’t drown in AI news. We cut through the noise - filtering, ranking and summarizing the most important AI news, breakthroughs and research daily. Follow topics that matter to you and stay ahead.
