Dina iki, kita ngluncurake versi anyar saka ChatGPT Images(mbukak ing jendhela anyar), sing didhukung model generasi gambar unggulan anyar kita. Saiki, apa wae sampeyan nggawe saka nol utawa nyunting foto, sampeyan bakal entuk asil sing cocog karo sing mbayang ing pikiran. Model iki nggawe suntingan presisi nalika tetep njaga detail, lan ngasilake gambar nganti 4x luwih cepet. Bebarengan karo kuwi, kita ngenalake fitur Images(mbukak ing jendhela anyar) anyar ing ChatGPT, dirancang supaya generasi gambar dadi nyenengake—ngobong inspirasi lan nggampangake eksplorasi kreatif.
Model Images anyar iki wiwit diluncurake dina iki ing ChatGPT kanggo kabeh pangguna, lan kasedhiya ing API minangka GPT Image 1.5. Pengalaman Images anyar ing ChatGPT uga wiwit diluncurake dina iki kanggo mayoritas pangguna, dene akses Business lan Enterprise bakal teka mengko.
Saiki, nalika sampeyan njaluk suntingan kanggo gambar sing diunggah, model iki luwih bisa manut karo maksud sampeyan—nganti menyang detail cilik—mung ngowahi apa sing sampeyan jaluk nalika tetep njaga unsur kaya pencahayaan, komposisi, lan tampilan wong supaya konsisten ing input, output, lan suntingan sabanjure.
Iki mbukak asil sing cocog karo maksud sampeyan—suntingan foto sing luwih migunani, coba-cocog sandhangan lan gaya rambut sing luwih meyakinkan, uga filter gaya lan transformasi konseptual sing njaga inti gambar asli. Bebarengan, peningkatan iki ateges ChatGPT bisa tumindak kaya studio kreatif ing kanthongmu, bisa kanggo suntingan praktis lan reimajinasi ekspresif.
Model iki unggul ing macem-macem jinis panyuntingan—kalebu nambah, nyuda, nggabungake, nyawijikake, lan mindhah—supaya sampeyan entuk owah-owahan sing dikarepake tanpa kelangan apa sing ndadekake gambar kasebut istimewa.
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.
Kreativitas model iki katon cetha liwat transformasi sing ngowahi lan nambah unsur—kaya teks lan tata letak—kanggo nguripake gagasan, nalika tetep njaga detail penting. Transformasi iki bisa digunakake kanggo konsep sing prasaja nganti sing luwih ruwet, lan gampang dicoba nganggo gaya lan ide prasetel ing fitur ChatGPT Images(mbukak ing jendhela anyar) anyar—tanpa perlu prompt sing ditulis.
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.
Model iki ngetutake instruksi luwih bisa diandelake tinimbang versi awal kita. Iki ndadekake suntingan luwih presisi uga komposisi asli sing luwih ruwet, ing ngendi hubungan antarunsur dijaga kaya sing dikarepake.
Anyar
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
Sadurunge
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
Model iki maju maneh ing rendering teks, bisa nangani teks sing luwih padhet lan luwih cilik.
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.
Model iki uga ningkatake dimensi tambahan liyane sing ndadekake output luwih langsung migunani, kayata nampilake akeh rai cilik lan sepira alamine tampilan output.
Anyar
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…
Sadurunge
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…
Saliyane ngasilake gambar kanthi njlentrehake apa sing pengin dideleng ing pesen, kita ngenalake omah khusus kanggo Images(mbukak ing jendhela anyar) ing ChatGPT—kasedhiya ing sidebar liwat aplikasi seluler lan ing chatgpt.com—supaya njelajah lan nyoba gambar dadi luwih cepet lan luwih gampang. Iki kalebu puluhan filter lan prompt prasetel kanggo miwiti inspirasi, sing dianyari kanthi rutin supaya cocog karo tren sing lagi muncul.
Bebarengan, peningkatan iki ngidini sampeyan nggawe gambar sing luwih cocog karo visi sampeyan, saka suntingan cilik nganti reimajinasi lengkap.
Kita nglakokake maneh akeh conto saka peluncuran generasi gambar awal kita kanggo ngevaluasi kinerja. Model iki nuduhake peningkatan sing cetha ing macem-macem kasus, sanajan asil isih durung sampurna. Sanadyan rilis iki nggambarake kemajuan sing migunani, isih ana ruang gedhe kanggo perbaikan ing iterasi sabanjure.
Anyar
create a poster of deep sea creatures at different depths, with a vertical ocean cutaway, styled in a beautiful japanese detailed anime style
Sadurunge
create a poster of deep sea creatures at different depths, with a vertical ocean cutaway, styled in a beautiful japanese detailed anime style
Isih ana sawetara ora akurat ilmiah, nanging ~70% bener lan grafisé luwih urip, ngindhari cropping sing kedadeyan kesusu.
GPT Image 1.5 ing API(mbukak ing jendhela anyar) menehi kabeh peningkatan sing padha kaya ChatGPT Images: model iki luwih unggul ing njaga lan nyunting gambar tinimbang GPT Image 1.
Sampeyan bakal ndeleng pangreksan sing luwih konsisten kanggo logo merek lan visual utama sajrone suntingan, mula cocog banget kanggo pemasaran lan karya merek kaya grafis lan pembuatan logo, uga kanggo tim e-commerce sing ngasilake katalog gambar produk lengkap (varian, adegan, lan sudut) saka siji gambar sumber.
Input lan output gambar saiki 20% luwih murah ing GPT Image 1.5 dibandhingake GPT Image 1, dadi sampeyan bisa ngasilake lan ngiterasi luwih akeh gambar kanthi anggaran sing padha.
Sampeyan bisa nyoba model anyar iki ing OpenAI Playground(mbukak ing jendhela anyar), ndeleng galeri(mbukak ing jendhela anyar), utawa maca pandhuan prompt(mbukak ing jendhela anyar) kanggo inspirasi.
Perusahaan gedhe lan startup ing macem-macem industri, kalebu piranti kreatif, e-commerce, piranti lunak pemasaran, lan liya-liyane wis nggunakake GPT Image 1.5.
Anyar
Sadurunge
“GPT Image 1.5 ngasilake gambar kanthi fidelitas dhuwur lan manut prompt sing kuwat, njaga komposisi, pencahayaan, lan detail sing rinci. Asilé resik, realistis, lan bisa diandelake, ndhukung alur kerja saka konsep menyang produksi sing luwih cepet ing platform kaya Wix. Adhedhasar uji coba lan kasus panggunaan utama sing kita delok ing Wix, konsistensi lan kualitasé saingan nganti ndadekake iki dadi salah siji model generasi gambar unggulan saiki.”
— Hila Gat, Kepala Riset AI lan Ilmu Data ing Wix
Model ChatGPT Images(mbukak ing jendhela anyar) anyar saiki wis wiwit diluncurake kanggo kabeh pangguna ChatGPT lan pangguna API ing saindenging jagad dina iki ing macem-macem permukaan. Iki bisa digunakake ing kabeh model, dadi sampeyan ora perlu milih apa-apa kanggo nggunakaké. Versi ChatGPT Images sing diluncurake luwih dhisik ing taun iki bakal tetep kasedhiya kanggo kabeh pangguna minangka GPT khusus(mbukak ing jendhela anyar).
Kita percaya yen kita isih ana ing wiwitan babagan apa sing bisa diwenehake generasi gambar. Pembaruan dina iki minangka langkah maju sing migunani lan isih akeh sing bakal teka, saka suntingan sing luwih rinci nganti output sing luwih sugih lan luwih detail ing macem-macem basa.
Pangarang
Kontributor
Pimpinan Proyek
Gabriel Goh — Pimpinan Riset
Adele Li — Pimpinan Produk
Bill Peebles — Pimpinan Sora
Aditya Ramesh — Pimpinan Simulasi Donya
Mark Chen — Chief Research Officer
Prafulla Dhariwal — Pimpinan Multimodal
Tim Inti
Alex Fang, Alex Yu, Ben Wang, Bing Liang, Boyuan Chen, Charlie Nash, David Medina, Dibya Bhattacharjee, Jianfeng Wang, Kenji Hata, Kiwhan Song, Mengchao Zhong, Mike Starr, Yuguang Yang
Kontributor Riset
Bram Wallace, Dmytro Okhonko, Haitang Hu, Kshitij Gupta, Li Jing, Lu Liu, Peter Zhokhov, Qiming Yuan, Senthil Purushwalkam, Yizhen Zhang
Inferensi Inti
Adam Tart, Alyssa Huang, Andrew Braunstein, Jane Park, Karen Li, Tomer Kaftan
Kolaborator Riset
Aditya Ramesh, Alex Nichol, Andrew Kondrich, Andrew Liu, Benedikt Winter, Bill Peebles, Connor Holmes, Cyril Zhang, Daniel Geng, Eric Mintun, James Betker, Jamie Kiros, Manuka Stratta, Martin Li, Raoul de Liedekerke, Ricky Wang, Ruslan Vasilev, Vladimir Chalyshev, Welton Wang, Wyatt Thompson, Yaming Lin
Kolaborator Inferensi
Jiayu Bai, Kevin King, Stanley Hsieh, Weiyi Zheng
Data & Evaluasi
Alexandra Barr, Aparna Dutta, Arshi Bhatnagar, Chao Yu, Charlotte Cole, Dragos Oprica, Emma Tang, Gowrishankar Sunder, Henry Baer, Ian Sohl, James Park Lennon, Jason Xu, Peilin Yang, Somay Jain, Szi-chieh Yu, Wesam Manassra, Xiaolei Zhu, Yilei Qian
Terapan
Affonso Reis, Alan Gou, Alexandra Vodopianova, Amandeep Grewal, Andi Liu, Andrew Sima, Angus Fletcher, Antonia Woodford, Arun Eswara, Benny Wong, Bharat Rangan, Boyang Niu, Bridget Collins, Bryan Brandow, Callie Riggins Zetino, Chris Wendel, Ethan Chang, Gilman Tolle, Greg Hochmuth, Ibrahim Okuyucu, Jesse Chand, Jesse Hendrickson, Jiayu Bai, Jimmy Lin, Johan Cervantes, Kan Wu, Liam Esparraguera, Maja Wichrowska, Matthew Ferrari, Murat Yesildal, Nikunj Handa, Nithanth Kudige, Ola Okelola, Osman Khwaja, Peter Argany, Peter Bakkum, Peter Vidani, Richard Zadorozny, Rohan Sahai, Savelii Bondini, Sean Chang, Vickie Duong, Victoria Huang, Xiaolin Hao, Xueqing Li
Keamanan, Sistem Keamanan, Integritas, Kebijakan & Kepercayaan
Abby Fanlo Susk, Adam Wells, Aleah Houze, Annie Cheng, Artyi Xu, Carolina Paz, David Abelman, Femi Alamu, Jay Wang, Jeremiah Currier, Jesika Haria, Mariya Guryeva, Max Burkhardt, Paige Walker, Pedro Aguilar, Rutsu Koshimizu, Sam Toizer, Savannah Heon, Tom Rubin, Tonia Osadebe, Willow Primack, Zoe Stoll
Operasi Produk, Manajemen Program lan Tata Kelola
Antonio Di Francesco, Filippo Raso, Grace Wu, Josh Metherd, Ruth Costigan
Legal
Ally Bennett, Tony Song, Tyce Walters
Komunikasi, Pemasaran, Komunitas, Desain & Kreatif
Akash Iyer, Alex Baker-Whitcomb, Angie Luo, Anne Oburgh, Antonia Richmond, Annie Tsang, Ashley Tyra, Bailey Richardson, Brandon McGraw, Cary Hudson, Dana Palmie, Evan Corrigan, Gaby Raila, Indgila Samad Ali, James Anderson, Jeremy Schwartz, Jordan Liss, Juan Garza, Julie Steele, Kara Zichittella, Karn Piluntanadilok, Kendal Peirce, Kim Baschet, Leah Anise, Livvy Pierce, Maria Clara M. Fleury Osorio, Minnia Feng, Nick Ciffone, Nick Forland, Niko Felix, Paige Ford, Rachel Puckett, Rishabh Aggarwal, Rusty Rupprecht, Souki Mansoor, Tasia Potasinski, Taya Christianson, Vasundhara Mudgil, Whitney Ferris, Yara Khakbaz, Zach Brock, Zoë Silverman
Matur Nuwun Khusus
Amy Yang, Arvin Wu, Avital Oliver, Brandon McKinzie, Chak Li, Chris Lu, David Duxin, Dian Ang Yap, Gabriel Petersson, Guillaume Leclerc, Hazel Byrne, Henry Aspegren, Jennifer Luckenbill, Ji Lin, Joseph Mo, Julius Hochmuth, Liunian (Harold) Li, Long Ouyang, Mariano López, Michael Zhang, Ravi Teja Mullapudi, Suvansh Sanjeev, Varun Shetty, Wenda Zhou
Eksekutif
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
