OpenAI Inc.
12/16/2025 | News release | Distributed by Public on 12/16/2025 12:14
The new ChatGPT Images is here
Today, we're releasing a new version of ChatGPT Images (opens in a new window), powered by our new flagship image generation model. Now, whether you're creating something from scratch or editing a photo, you'll get the output you're picturing. It makes precise edits while keeping details intact, and generates images up to 4x faster. Alongside, we're introducing a new Images feature (opens in a new window)within ChatGPT, designed to make image generation delightful-to spark inspiration and make creative exploration effortless.
The new Images model and feature are rolling out today in ChatGPT for all users, and in the API as GPT Image 1.5.
Precise edits that preserve what matter
Now, when you ask for edits to an uploaded image, the model adheres to your intent more reliably-down to the small details-changing only what you ask for while keeping elements like lighting, composition, and people's appearance consistent across inputs, outputs, and subsequent edits.
This unlocks results that match your intent-more useful photo edits, more believable clothing and hairstyle try-ons, alongside stylistic filters and conceptual transformationsthat retain the essence of the original image. Together, these improvements mean ChatGPT can act as a creative studio in your pocket, capable of both practical edits and expressive reimaginings.
Editing
The model excels at different types of editing-including adding, subtracting, combining, blending, and transposing-so you get the changes you want without losing what makes the image special.
From party to livestreamLA skateboarding
Combine the two men and the dog in a 2000s film camera-style photo of them looking bored at a kids birthday party.
Add chaotic kids in the background throwing things and screaming.
Change the man on the left to a hand-drawn retro anime style, the dog to plushie style, keep the man on the right and background scenery the way they are.
Put them all in OpenAI sweaters that look like this.
Now remove the two men, just keep the dog, and put them in an OpenAI livestream that looks like the attached image.
Creative transformations
The model's creativity shines through transformations that change and add elements-like text and layout-to bring ideas to life, while preserving important details. These transformations work for both simple and more intricate concepts, and are easy to try using preset styles and ideas in the new ChatGPT Images (opens in a new window)feature-no written prompt required.
Movie poster80s fitness instructorGlam dollOrnamentFashion adDress-up characterPaintingDrink ad
Make an old school golden age hollywood movie poster of a movie called 'codex' from the image of these two men. feel free to change their costumes to fit the times
Change the names of the actors to Wojciech Zaremba (left) and Greg Brockman (right)
Directed by Sam Altman, produced by Fidji Simo. A Feel the AGI Pictures Production.
Instruction following
The model follows instructions more reliably than our initial version. This enables more precise edits as well as more intricate original compositions, where relationships between elements are preserved as intended.
New
draw a 6x6 grid
Make a 6 (columns) by 6 (rows) grid grid of:
Row 1: the Greek letter beta, a beach ball, a lemon, a robot, a fish tank, a frog
Row 2: a praying mantis, an expensive watch, a baththub, a pair of sunglasses, a colorful butterfly, an envelope
Row 3: a stamp, a picture frame, a steaming dumpling, the word "miracle", a pair of skis, the letter Z
Row 4: a toilet, a subway token, a mute icon, a bottle of perfume, a dragonfly, a skateboard helmet
Row 5: a Bluetooth icon, the number 13, a green heart, a rubik's cube, a Canada goose, a soldier's helmet
Row 6: a white dog, a life jacket, a knot, a keyboard, a tissue box, the number 14
Previous
draw a 6x6 grid
Make a 6 (columns) by 6 (rows) grid grid of:
Row 1: the Greek letter beta, a beach ball, a lemon, a robot, a fish tank, a frog
Row 2: a praying mantis, an expensive watch, a baththub, a pair of sunglasses, a colorful butterfly, an envelope
Row 3: a stamp, a picture frame, a steaming dumpling, the word "miracle", a pair of skis, the letter Z
Row 4: a toilet, a subway token, a mute icon, a bottle of perfume, a dragonfly, a skateboard helmet
Row 5: a Bluetooth icon, the number 13, a green heart, a rubik's cube, a Canada goose, a soldier's helmet
Row 6: a white dog, a life jacket, a knot, a keyboard, a tissue box, the number 14
Text rendering
The model takes another step ahead in text rendering, capable of handling denser and smaller text.
Markdown renderingCalorie infographicCoding
There is a newspaper on a desk. The newspaper shows the markdown below laid out as a **natural** newspaper article. Preserve all content, formatting, and numbers exactly. The image should be tall.
# Introducing GPT-5.2
### *The most advanced frontier model for professional work and long-running agents*
**December 11, 2025**
---
We are introducing **GPT-5.2**, the most capable model series yet for professional knowledge work.
Already, the average ChatGPT Enterprise user says AI saves them 40-60 minutes a day, and heavy users say it saves them more than 10 hours a week. We designed GPT-5.2 to unlock even more economic value for people; it's better at creating spreadsheets, building presentations, writing code, perceiving images, understanding long contexts, using tools, and handling complex, multi-step projects.
GPT-5.2 sets a new state of the art across many benchmarks, including GDPval, where it outperforms industry professionals at well-specified knowledge work tasks spanning 44 occupations.
---
## Benchmark highlights
| Benchmark | Domain | GPT-5.2 Thinking | GPT-5.1 Thinking |
|---|---|---:|---:|
| GDPval (wins or ties) | Knowledge work tasks | **70.9%** | 38.8% (GPT-5) |
| SWE-Bench Pro (public) | Software engineering | **55.6%** | 50.8% |
| SWE-bench Verified | Software engineering | **80.0%** | 76.3% |
| GPQA Diamond (no tools) | Science questions | **92.4%** | 88.1% |
| CharXiv Reasoning (w/ Python) | Scientific figure questions | **88.7%** | 80.3% |
| AIME 2025 (no tools) | Competition math | **100.0%** | 94.0% |
| FrontierMath (Tier 1-3) | Advanced mathematics | **40.3%** | 31.0% |
| FrontierMath (Tier 4) | Advanced mathematics | **14.6%** | 12.5% |
| ARC-AGI-1 (Verified) | Abstract reasoning | **86.2%** | 72.8% |
| ARC-AGI-2 (Verified) | Abstract reasoning | **52.9%** | 17.6% |
---
Notion, Box, Shopify, Harvey, and Zoom observed that GPT-5.2 demonstrates state-of-the-art long-horizon reasoning and tool-calling performance. Databricks, Hex, and Triple Whale found GPT-5.2 to be exceptional at agentic data science and document analysis tasks. Cognition, Warp, Charlie Labs, JetBrains, and Augment Code report that GPT-5.2 delivers state-of-the-art agentic coding performance, with measurable improvements in areas such as interactive coding, code reviews, and bug finding.
In ChatGPT, GPT-5.2 Instant, Thinking, and Pro will begin rolling out today, starting with paid plans. In the API, they are available now to all developers.
Overall, GPT-5.2 brings significant improvements in general intelligence, long-context understanding, agentic tool-calling, and vision-making it better at executing complex, real-world tasks end-to-end than any previous model.
Now change the article to the markdown below:
# Introducing GPT-Image-1.5
### *The new and improved ChatGPT Images*
**December 16, 2025**
---
Today, we're introducing a new and improved version of ChatGPT Images, powered by our best image generation model yet. With stronger instruction following and more precise editing, ChatGPT Images delivers the changes you ask for while keeping important details like facial likeness consistent across edits-now with generation speeds up to **4× faster**, making it easier to iterate and explore ideas with less waiting.
This is our most capable general-purpose text-to-image model to date, with more expressive transformations, improved dense text rendering, and more natural-looking results. Whether you're making a tiny fix or a total reinvention, you can simply say what you want-or choose from preset styles and ideas in the new Images experience-and ChatGPT handles the rest, delivering results that are both useful and compelling, and better match your intent.
The new Images model and experience is beginning to roll out today in ChatGPT for all users, and in the API as **GPT-Image-1.5**.
---
## Results that match your intent
The model now follows instructions more reliably-down to the small details-changing what you ask for while able to keep elements like lighting, composition, and likeness consistent across inputs, outputs, and subsequent edits.
This unlocks results that match your intent-more useful photo edits, more believable clothing and hairstyle try-ons, alongside stylistic filters and conceptual transformations that retain the essence of the original image. Together, these improvements mean ChatGPT can act as a creative studio in your pocket, capable of both practical edits and expressive reimaginings.
### Editing
The model excels at different types of editing so you get the changes you want without losing what makes the image special.
### Creative Transformations
The model's creativity shines with creative transformations, changing and adding elements-like text and layout-that help the concept come to life while maintaining important details.
### Instruction Following
The model is able to better follow instructions versus GPT Image 1.0.
### Text Rendering
The model takes another step ahead in text rendering, capable of handling denser and smaller text.
---
## A new creation space
In addition to asking for images through ChatGPT by describing what you'd like to see, we're also introducing a dedicated Images experience in the ChatGPT sidebar to make exploring and trying images easier and quicker. This includes preset filters and trending prompts to jump-start inspiration, as well as a one-time likeness upload so you can reuse your appearance across future creations without the need to go through your camera roll again.
Together, these upgrades let you create images that better match your vision, from small edits to full reimaginings. Images now render up to four times faster, and you can continue generating new images while others are still in progress-so you can explore more ideas without waiting.
Additional quality improvements
The model also improves on additional dimensions that translate to more immediately usable outputs, like rendering many small faces and how natural outputs look.
1970s LondonMany small facesDiver playing pianoPhoto with glare
New
make a scene in chelsea, london in the 1970s, photorealistic, everything in focus, with tons of people, and a bus with an advertisement for "ImageGen 1.5" with the OpenAI logo and subtitle "Create what you imagine". Hyper-realistic amateur photography, iPhone snapshot quality…
Previous
make a scene in chelsea, london in the 1970s, photorealistic, everything in focus, with tons of people, and a bus with an advertisement for "ImageGen 1.5" with the OpenAI logo and subtitle "Create what you imagine". Hyper-realistic amateur photography, iPhone snapshot quality…
A new creation space
In addition to generating images by describing what you'd like to see in a message, we're introducing a dedicated home for Images (opens in a new window)in ChatGPT-available in the sidebar through the mobile app and on chatgpt.com-to make exploring and trying images faster and easier. It includes dozens of preset filters and prompts to jump-start inspiration, updated regularly to reflect emerging trends.
Together, these upgrades let you create images that better match your vision, from small edits to full reimaginings.
Improvements and limitations
We reran many of the examples from our initial image generation launch to evaluate performance. The model shows clear improvements across a range of cases, though results remain imperfect. While this release represents meaningful progress, there is still significant room for improvement in future iterations.
Deep sea poster (Improvement)World capitals (Improvement)Styles (Limitation)Multiple faces (Limitation)Multilingual (Limitation)
New
create a poster of deep sea creatures at different depths, with a vertical ocean cutaway, styled in a beautiful japanese detailed anime style
Previous
create a poster of deep sea creatures at different depths, with a vertical ocean cutaway, styled in a beautiful japanese detailed anime style
Still some scientific inaccuracies, but ~70% correct and much more vivid graphics, avoids premature cropping.
GPT Image 1.5 in the API
GPT Image 1.5 in the API (opens in a new window)delivers all the same improvements as ChatGPT Images: it's stronger at image preservation and editing than GPT Image 1.
You'll see more consistent preservation of branded logos and key visuals across edits, making it well suited for marketing and brand work like graphics and logo creation, and for ecommerce teams generating full product image catalogs (variants, scenes, and angles) from a single-source image.
Image inputs and outputs are now 20% cheaper in GPT Image 1.5 as compared to GPT Image 1, so you can generate and iterate on more images with the same budget.
You can try the new model in the OpenAI Playground (opens in a new window)or read the prompt guide (opens in a new window)for inspiration.
Enterprises and startups across industries, including creative tools, e-commerce, marketing software, and more are already using GPT Image 1.5.
WixCanvaHiggsfieldFigma WeaveEnvato
New
Previous
"GPT Image 1.5 generates high-fidelity images with strong prompt adherence, preserving composition, lighting, and fine-grained detail. The results are clean, realistic, and reliable, supporting faster concept-to-production workflows on platforms like Wix. Based on our testing and the main use cases we see at Wix, the consistency and quality compete to make it one of the flagship image generation models today."
- Hila Gat, Head of AI Research and Data Science at Wix
Availability
The new ChatGPT Images is rolling out now to all ChatGPT users and API users globallytoday across surfaces. It works across models, so you don't need to select anything in order to use it. The version of ChatGPT Images that launched earlier this year will remain available to all users as a custom GPT (opens in a new window).
We believe we're still at the beginning of what image generation can enable. Today's update is a meaningful step forward with more to come, from finer-grained edits to richer, more detailed outputs across languages.
Author
OpenAIContributors
Project Leadership
Gabriel Goh - Research Lead
Adele Li - Product Lead
Bill Peebles - Sora Lead
Aditya Ramesh - World Simulation Lead
Mark Chen - Chief Research Officer
Prafulla Dhariwal - Multimodal Lead
Core Team
Alex Fang, Alex Yu, Ben Wang, Boyuan Chen, Charlie Nash, Dibya Bhattacharjee, David Medina, Jianfeng Wang, Kenji Hata, Kiwhan Song, Yuguang Yang, Mengchao Zhong, Bing Liang, Mike Starr
Research Contributors
Bram Wallace, Dmytro Okhonko, Senthil Purushwalkam, Kshitij Gupta, Haitang Hu, Peter Zhokhov, Yizhen Zhang,Li Jing, Qiming Yuan, Lu Liu
Core Inference
Adam Tart, Alyssa Huang, Andrew Braunstein, Jane Park, Karen Li, Tomer Kaftan
Research Collaborators
Daniel Geng, Manuka Stratta, Cyril Zhang, Aditya Ramesh, James Betker, Bill Peebles, Andrew Kondrich, Ricky Wang, Vladimir Chalyshev, Alex Nichol, Raoul de Liedekerke, Wyatt Thompson, Andrew Liu, Benedikt Winter, Connor Holmes, Eric Mintun, Jamie Kiros, Martin Li, Welton Wang, Yaming Lin, Ruslan Vasilev
Inference Collaborators
Jiayu Bai, Kevin King, Stanley Hsieh, Weiyi Zheng
Data & Evaluation
Alexandra Barr, Aparna Dutta, Charlotte Cole, James Park, Lennon Szi-chieh Yu, Xiaolei Zhu, Henry Baer, Hazel Byrne, Jennifer Luckenbill, Mariano López, Wesam Manassra, Somay Jain, Peilin Yang, Jason Xu, Emma Tang, Dragos Oprica, Yilei Qian, Gowrishankar Sunder, Arshi Bhatnagar, Chao Yu, Ian Sohl
Applied
Alan Gou, Andrew Sima, Angus Fletcher, Benny Wong, Boyang Niu, Callie Riggins Zetino, Greg Hochmuth, Jesse Hendrickson, Johan Cervantes, Liam Esparraguera, Maja Wichrowska, Murat Yesildal, Nithanth Kudige, Osman Khwja, Peter Argany, Savelii Bondini, Vickie Duong, Xueqing Li, Affonso Reis, Amandeep Grewal, Arun Eswara, Bharat Rangan, Bridget Collins, Bryan Brandow, Ethan Chang, Gilman Tolle, Jiayu Bai, Kan Wu, Matthew Ferrari, Peter Vidani, Richard Zadorozny, Sean Chang, Victoria Huang, Xiaolin Hao, Hairol Ma, Alexandra Vodopianova, Ibrahim Okuyucu, Jesse Chand, Antonia Woodford, Chris Wendel, Jessie Li, Rohan Sahai, Peter Bakkum, Nikunj Handa, Andi Liu, Ola Okelola, Jimmy Lin
Safety, Safety Systems, Integrity, Policy & Trust
Tonia Osadebe, Abby Fanlo Susk, Adam Wells, Aleah Houze, Annie Cheng, Artyi Xu, Carolina Paz, Sam Toizer, Savannah Heon, Zoe Stoll, Tom Rubin, David Abelman, Femi Alamu, Willow Primack, Jeremiah Currier, Rutsu Koshimizu, Pedro Aguilar, Jesika Haria, Mariya Guryeva, Max Burkhardt, Paige Walker
Product Operations, Program Management and Governance
Antonio Di Francesco, Ruth Costigan, Grace Wu, Filippo Raso, Josh Metherd
Legal
Tyce Walters, Ally Bennett, Tony Song
Communications, Marketing, Community, Design & Creative
Minnia Feng, Karn Piluntanadilok, Alex Baker-Whitcomb, Jordan Liss, Ashley Tyra, Bailey Richardson, Gaby Raila, Julie Steele, Leah Anise, Niko Felix, Angie Luo, Antonia Richmond, Brandon McGraw, Dana Palmie, Cary Hudson, Evan Corrigan, James Anderson, Whitney Ferris, Jeremy Schwartz, Yara Khakbaz, Kendal Peirce, Kim Baschet, Livvy Pierce, Nick Forland, Nick Ciffone, Paige Ford, Rachel Puckett, Rishabh Aggarwal, Taya Christianson, Souki Mansoor, Tasia Potasinski, Vasundhara Mudgil, Anne Oburgh, Indgila Samad Ali, Akash Iyer, Maria Clara M. Fleury Osorio, Juan Garza, Kara Zichittella, Rusty Rupprecht, Zoë Silverman, Annie Tsang, Zach Brock
Special Thanks
Julius Hochmuth, Henry Aspegren, Michael Zhang, Avital Oliver, Arvin Wu, Chak Li, Joseph Mo, Wenda Zhou, Amy Yang, Liunian (Harold) Li, Ji Lin, Chris Lu, Suvansh Sanjeev, Guillaume Leclerc, Dian Ang Yap, Brandon McKinzie, Ravi Teja Mullapudi, Long Ouyang, Gabriel Petersson, David Duxin, Varun Shetty
Exec
Fidji Simo, Hannah Wong, Jakub Pachocki, Jason Kwon, Johannes Heidecke, Kate Rouch, Lauren Itow, Mark Chen, Mia Glaese, Nick Ryder, Nick Turley, Prafulla Dhariwal, Sam Altman, Sulman Choudhry
OpenAI Inc. published this content on December 16, 2025, and is solely responsible for the information contained herein. Distributed via Public Technologies (PUBT), unedited and unaltered, on December 16, 2025 at 18:14 UTC. If you believe the information included in the content is inaccurate or outdated and requires editing or removal, please contact us at [email protected]