Introducing ChatGPT Images 2.5 | OpenAISkip to main contentResearchProductsBusinessDevelopersCompanyFoundation(opens in a new window)Log inTry ChatGPT(opens in a new window)ResearchProductsBusinessDevelopersCompanyFoundation(opens in a new window)Try ChatGPT(opens in a new window)LoginOpenAISeptember 8, 2026ProductIntroducing ChatGPT Images 2.5IntroducingChatGPT Images 2.5ChatGPT Images 2.5Sharper details, faster generation, more precise editing, and better tools for creating and sharing.Loading…ShareImage fidelity as you createImage fidelity as you createPrecision editingMulti-turn editing consistencyIntelligence and style improvementsUse Sketch to draw your idea to lifeStructure your prompts for better resultsPass your best ideas alongImages 2.5 in the APIOur commitment to safetyPricing and availabilityImage fidelity as you createPrecision editingMulti-turn editing consistencyIntelligence and style improvementsUse Sketch to draw your idea to lifeStructure your prompts for better resultsPass your best ideas alongImages 2.5 in the APIOur commitment to safetyPricing and availabilityEvery week, people create more than 3 billion images across ChatGPT Images and the GPT‑Image models in the API. Today, we’re expanding what you can create with ChatGPT Images 2.5—our new state-of-the-art image model that brings sharper details, more precise editing, and faster generation to your creative workflows.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. 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.In ChatGPT, we’re introducing product features that give you more control over the creative process. Sketch⁠(opens in a new window) is a new feature that lets you draw directly in ChatGPT as a reference for your final image. Templates make it easier to start creating across some of the most popular image formats, like flyers and product photos. You can also now place comments directly on images for more focused editing, and you can share prompts you’ve used to let others try your ideas with their own photos and details.Images 2.5 is available to all ChatGPT, ChatGPT Work, and Codex users across desktop, mobile, and web.For developers, we’re introducing two new models in the API. GPT‑Image‑2.5 Flare brings the same improvements in quality, editing, and speed, and GPT‑Image‑2.5 Sunburst offers an extra level of precision for detailed creative work with longer generation times.Image fidelity as you createThe most meaningful images feel grounded in the real-life people, places, and memories they’re based on. Images 2.5 is better at working from reference photos to transform familiar subjects across new settings, visual styles, and compositions. Image subjects look more recognizable, lighting and textures feel more natural, and distinctive features are more likely to carry through.For teams building with the API, this same fidelity makes reference-led workflows more reliable, so variations can stay anchored to the original source.Remixed baby portraitDog in costumeHeadshot from photoboothComposite party photoMaking the bedPrecision editingWe’ve made it easier for you to make focused edits, so you end up with final images that are more aligned with what you actually had in mind. Images 2.5 is better at editing only what you’ve asked for, while keeping the rest of the details the same—even with more complex subjects and backgrounds.For developers using the Images API, this gives users the ability to update a single element—such as a product, background, or piece of copy—while preserving the subject, composition, and brand treatment around it.The following videos are made up of multiple images, highlighting the model’s improved ability to follow precise editing instructions.Full-body editsMulti-city ticketMulti-turn editing consistencyDuring longer ChatGPT conversations, Images 2.5 follows specific editing instructions more reliably across multiple edits. Earlier changes are more likely to stay consistent, and each new edit builds on the work you’ve already done without degrading image quality over time.That consistency also matters in production workflows, where developers need to make targeted changes without rebuilding the entire asset.The following videos are made up of multiple images, highlighting the model’s improved ability to maintain image quality over multiple turns.Cube rotationTravel infographicBirthday candlesIntelligence and style improvementsImages 2.5 is better at understanding complex visual instructions and translating them into coherent results. Images that include real-world information have more accurate content, and the model can handle more complex layouts including transparent backgrounds. It’s also better at reflecting visual styles, so your images are more aligned with your artistic vision.For developers and businesses, this makes complex creative briefs more dependable. The model is more likely to retain the requested visual direction, composition, and individual details, instead of drifting as instructions become more specific. That matters when generating a series of on-brand creative assets, UI concepts that preserve a given hierarchy, or presentation visuals that fit a defined structure.Use Sketch to draw your idea to lifeSometimes the clearest way to explain an idea is by drawing it.We’re introducing Sketch, a new feature which lets you draw right in ChatGPT and use it as a visual guide. Now you can quickly sketch the layout of a room, the contour of an outfit you’re concepting, or just a funny doodle, and ChatGPT will turn your rough art into a complete image. Add a description of the style and any other details you want to make sure it reflects your vision.You don’t need to be a professional artist—this is just another way to get your final image closer to what you have in mind. To try it yourself⁠(opens in a new window), just type “@Sketch” in ChatGPT.Structure your prompts for better resultsAt times you may have a clear idea of what you want to make—you just need some help getting started.We’re introducing templates for some of the most popular creative formats. Instead of starting with a blank canvas, you can choose a template like “Poster” or “Merch” and add details like information to convey, design elements, or styles to personalize your results.Pass your best ideas alongOften you end up with an image that’s too good not to share.Now when you share an image, you can also choose to include the prompt that got you there. Someone else can then run with the same idea, bringing in their own images and details to make a version that feels like their own.For example, try out this prompt⁠(opens in a new window) that’s currently going viral to see what you would’ve looked like in the ’80s!Images 2.5 in the APIDevelopers are building image generation workflows into products used by creative, marketing, retail, and media teams every day with the Images API.We’re releasing two new image models in the API:GPT‑Image‑2.5 Flare brings the same improvements in quality, editing, and speed to the API and is the default choice for most applications, delivering higher-quality images than GPT‑Image‑2 at 50% lower latency. It’s well suited to everything from creator and social content to product experiences, visual search, rapid image prototyping, and high-volume generation.GPT‑Image‑2.5 Sunburst is built for premium visual workflows that benefit from tighter control across edits. Use it for creative and editing workflows like production-ready campaign creative or polished product imagery.Here’s what early customers have to say about the new models:1 of 3“What impressed us most about GPT‑Image‑2.5 Flare is how well it understands what not to change. You can make a meaningful edit without losing the character, composition or visual identity of the original image. That’s incredibly important for the way creators and teams actually work across film, UGC and advertising. And when you combine that level of control with the speed, quality and cost, GPT‑Image‑2.5 Flare really stands out.”Axultan Alimkulov, Head of Product at Higgsfield AI⁠(opens in a new window)“Adobe Firefly, our creative AI studio, gives creators flexibility and control as they move from idea to finished content, bringing together leading AI models and Adobe's pro-grade tools in one place. We're excited to expand that choice with OpenAI's latest GPT‑Image‑2.5 models now in Firefly, bringing faster generation and resolution consistency that keep images sharp and photorealistic through every refinement.”Matt Chotin, Senior Director, Product at Adobe“GPT‑Image‑2.5 is an impressive step forward. In our evaluations, Flare delivers high-quality images at two to four times the speed of GPT‑Image‑2. With improved transparent-background generation, it is an excellent fit for creative work on Manus, from brand assets to presentations and websites.”Lucky Liao, Evaluation Team at ManusHiggsfield AIAdobeManusHiggsfield AIAdobeManusOur commitment to safetyWe’re building image generation to be useful, creative, and safe. ChatGPT Images 2.5 builds on our existing safeguards, with checks on prompts and images to help prevent harmful outputs. We continue to use C2PA metadata and invisible watermarking to help identify images made with our tools. You can read more about our evaluations and approach in the system card⁠(opens in a new window).Pricing and availabilityImages 2.5 is rolling out today to ChatGPT, ChatGPT Work, and Codex users across all tiers on desktop, mobile, and web.GPT‑Image‑2.5 Sunburst and GPT‑Image‑2.5 Flare are available in the API. See pricing details here.⁠2026ChatGPTAuthorOpenAIKeep readingView allGPT-6 Astra: A new generation of intelligenceResearchSep 3, 2026ChatGPT can now connect to healthcare sourcesProductSep 1, 2026A milestone in expanding access to AIProductAug 31, 2026ResearchResearch IndexResearch OverviewEconomic ResearchLatest AdvancementsGPT-6GPT-5.6GPT-5.5GPT-5.4SafetySafety ApproachDeployment Safety(opens in a new window)Security & PrivacyTrust & TransparencyProductsChatGPT(opens in a new window)ChatGPT Business(opens in a new window)ChatGPT Enterprise(opens in a new window)ChatGPT for Education(opens in a new window)CodexRelease NotesAPI PlatformOverviewAPI Log In(opens in a new window)Docs(opens in a new window)BusinessOverviewSolutionsResourcesCustomer StoriesPartner NetworkContact SalesDevelopersApps SDK(opens in a new window)Open ModelsDocs(opens in a new window)Resources(opens in a new window)Developer Forum(opens in a new window)CompanyAbout UsOur CharterCareersNewsSupportHelp Center(opens in a new window)MoreStoriesAcademySupply Co.LivestreamsPodcastRSSTerms & PoliciesTerms of UsePrivacy PolicyOther Policies (opens in a new window)(opens in a new window)(opens in a new window)(opens in a new window)(opens in a new window)(opens in a new window)(opens in a new window)OpenAI © 2015–2026Your privacy choicesEnglishUnited StatesChatGPT Images 2.5Input

ChatGPT Images 2.5 represents a state-of-the-art image model designed to enhance creative workflows by delivering sharper details, faster generation speeds, more precise editing capabilities, and improved tools for creating and sharing visual content. This new iteration focuses heavily on enhancing image fidelity, enabling more reliable multi-turn editing consistency, and incorporating greater intelligence and style awareness into the generation process. The model achieves this by producing images with more natural lighting and richer textures, demonstrating improved ability to preserve subjects in reference photos, and adhering more reliably to complex editing instructions across successive interactions. Furthermore, generation latency has been reduced by up to fifty percent compared to Images 2.0, allowing users to iterate on concepts and refine ideas much more quickly.

The platform introduces several new features aimed at giving users greater control over the creative process. Sketch is a novel feature integrated directly into ChatGPT that allows users to draw ideas within the chat interface to serve as a visual reference for the final image; users can describe the desired style before generation, enabling them to translate rough art into complete images without needing professional artistic skills. To ease the starting process, templates are introduced for popular formats such as flyers and product photos, allowing users to personalize creations quickly with preset design elements. Additionally, users gain new functionalities to place comments directly on images for focused editing and the ability to share the prompts used to generate an image so others can iterate on the concept using their own source material.

For developers utilizing the API, two specialized models are introduced: GPT-Image-2.5 Flare and GPT-Image-2.5 Sunburst. GPT-Image-2.5 Flare is positioned as the default choice, offering the same quality, editing capacity, and speed improvements, and is optimized for high-volume generation, creator content, visual search, and rapid prototyping at fifty percent lower latency than GPT-Image-2.0. GPT-Image-2.5 Sunburst is designed for premium visual workflows that demand tighter control over edits, making it suitable for production-ready campaign creative or highly polished product imagery. Early feedback highlights the advantages of Flare, noting its superior ability to understand what not to change while executing meaningful edits without compromising the original character or composition, which is considered crucial in professional fields like film, user-generated content, and advertising, especially when combined with speed and cost efficiency.

The fidelity improvements of Images 2.5 are built on grounding images in real life, improving the transformation of familiar subjects across new settings, visual styles, and compositions while ensuring that distinctive features remain recognizable. In terms of editing precision, Images 2.5 excels at targeted edits, allowing users to modify a single element—such as a product or background—while rigorously preserving the subject, composition, and brand treatment surrounding it. A significant advancement is multi-turn editing consistency, where the model reliably adheres to specific editing instructions across extended conversations; earlier changes maintain greater consistency, allowing subsequent edits to build upon previous work without quality degradation.

Intelligence and style improvements allow the model to better comprehend complex visual instructions, resulting in more accurate content when generating images incorporating real-world information, handling complex layouts including transparent backgrounds effectively, and reflecting desired artistic visions with greater accuracy. This reliability is particularly beneficial for developers and businesses needing to generate series of on-brand assets, maintain specific hierarchies in UI concepts, or create presentation visuals adhering to a predefined structure.

In terms of safety and trust, the system incorporates existing safeguards augmented by checks on prompts and images to prevent harmful outputs, utilizing C2PA metadata and invisible watermarking to assist in identifying content generated by the tools. Images 2.5 is currently rolling out across all tiers of ChatGPT, ChatGPT Work, and Codex users on desktop, mobile, and web platforms, with the specialized API models available for developers.