Ngayon, inilalabas namin ang bagong bersyon ng ChatGPT Images, na pinapagana ng aming bagong pangunahing modelo ng image generation. Ngayon, kung ikaw ay gumawa ng isang bagay mula sa simula o nag-e-edit ng larawan, makukuha mo ang resulta na iyong iniisip. Gumagawa ito ng eksaktong pag-edit habang pinapanatili ang mga detalye tulad ng hitsura ng mga tao, at bumubuo ng mga larawan nang hanggang 4x na mas mabilis. Kasabay nito, ipinapakilala namin ang bagong feature na Larawan sa loob ng ChatGPT, na idinisenyo para gawing kasiya-siya ang pagbuo ng larawan—para magbigay ng inspirasyon at gawing madali ang malikhaing paggalugad
Ang bagong modelo at feature na larawan ay inilulunsad ngayon sa ChatGPT para sa lahat ng user, at sa API bilang gpt-image-1.5.
Ngayon, kapag humiling ka ng mga pag-edit sa na-upload na larawan, mas maaasahan ang modelo sa pagsunod sa iyong intensyon—hanggang sa maliliit na detalye—binabago lang ang iyong hinihiling habang pinapanatili ang mga element tulad ng ilaw, komposisyon, at hitsura ng mga tao na pare-pareho sa mga input, output, at sa mga kasunod na pag-edit.
Binubuksan nito ang mga resulta na tumutugma sa iyong intensyon—mas kapaki-pakinabang na pag-edit ng larawan, mas kapanipaniwalang pagsubok ng damit at hairstyle,kasabay ng stylistic na mga filter at konseptwal na mga pagbabago na pinapanatili ang esensya ng orihinal na larawan. Sama-sama, ang mga pagpapahusay na ito ay nangangahulugang puwedeng kumilos ang ChatGPT bilang creative studio sa iyong bulsa, na kayang gumawa ng parehong praktikal na mga pag-edit at malikhaing muling pag-iimagine.
Mahusay ang modelo sa iba't ibang uri ng pag-edit—kabilang ang pagdaragdag, pagbabawas, pagsasama, paghahalo, at paglipat—kaya makukuha mo ang mga pagbabagong gusto mo nang hindi nawawala ang espesyal na katangian ng larawan.
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.
Makikita ang pagkamalikhain ng modelo sa mga transformasyong nagbabago at nagdaragdag ng mga element, gaya ng text at layout, para mabigyang-buhay ang mga ideya habang pinananatili ang mahahalagang detalye. Gumagana ang mga transformasyong ito para sa parehong simple at mas masalimuot na mga konsepto, at madaling subukan gamit ang mga preset na istilo at ideya sa bagong ChatGPT Images(magbubukas sa bagong window) feature—hindi na kailangan ng nakasulat na prompt.
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.
Mas maaasahang sinusunod ng modelo ang mga tagubilin kaysa sa aming unang bersyon. Ini-enable nito ang mas tumpak na mga pag-edit pati na rin ang mas masalimuot na orihinal na komposisyon, kung saan napananatili ang mga ugnayan sa pagitan ng mga element ayon sa intensyon.
Bago
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
Nakaraan
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
Sumusulong pa ang modelo sa text rendering, na may kakayahang humawak ng mas siksik at mas maliliit na text.
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.
Pinapabuti rin ng modelo ang karagdagang mga dimensyon na nagreresulta sa mas agarang magagamit na mga output, tulad ng pag-render ng maraming maliliit na mukha at kung gaano ka-natural ang hitsura ng mga output.
Bago
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…
Nakaraan
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…
Bilang karagdagan sa pagbubuo ng mga larawan sa pamamagitan ng paglalarawan ng gusto mong makita sa mensahe, ipinapakilala namin ang dedikadong lugar para sa Mga Larawan(magbubukas sa bagong window) sa ChatGPT—magagamit sa sidebar sa pamamagitan ng mobile app at sa chatgpt.com—upang gawing mas mabilis at mas madali ang paggalugad at pagsubok ng mga larawan. Kasama nito ang dose-dosenang mga preset na filter at prompt para pasimulan ang inspirasyon, na regular na ina-update para ipakita ang mga umuusbong na trend.
Kapag pinagsama-sama, ang mga pag-upgrade na ito ay nagbibigay-daan sa iyong gumawa ng mga larawang mas tumutugma sa iyong pananaw, mula sa maliliit na pag-edit hanggang sa mga kumpletong pagbabago.
Pinapadali ng modelong ito ang mga daloy ng trabaho sa negosyo gamit ang mas mabilis na pagbuo ng imahe, tumpak na mga pag-edit, at pare-parehong mga detalyeng biswal sa iba't ibang mga pag-ulit. Maaaring galugarin ng mga team ang mga ideya, gumawa ng mga tiyak na pagbabago, at biswal na ipakita ang mga kumplikado o dry na konsepto, na sumusuporta sa mga use case sa marketing, disenyo, e-commerce, at panloob na komunikasyon.
Muli naming ginawa ang maraming halimbawa mula sa aming unang paglulunsad ng pagbuo ng larawan para suriin ang pagganap. Ipinapakita ng modelo ang malinaw na mga pagpapabuti sa iba't ibang kaso, kahit na nananatiling hindi perpekto ang mga resulta. Bagaman ang paglabas na ito ay kumakatawan sa makabuluhang pag-unlad, may malaki pang puwang para sa pagpapabuti sa mga susunod na bersyon.
Bago
create a poster of deep sea creatures at different depths, with a vertical ocean cutaway, styled in a beautiful japanese detailed anime style
Nakaraan
create a poster of deep sea creatures at different depths, with a vertical ocean cutaway, styled in a beautiful japanese detailed anime style
Mayroon pa ring ilang kamalian sa agham, ngunit dahil halos 70% tama at mas matingkad ang mga graphics, naiiwasan nito ang maagang pag-crop.
ang gpt-image-1.5 sa API ay naghahatid ng lahat ng parehong mga pagpapabuti sa ChatGPT Images: mas mahusay ito sa pagpepreserba ng mga larawan at pag-edit ng mga larawan kaysa sa GPT Image 1.
Makikita mo ang mas pare-parehong pagpapanatili ng mga branded na logo at mahahalagang visual sa mga pag-edit—na ginagawang angkop ito para sa marketing at gawaing may kinalaman sa brand tulad ng paglikha ng graphics at logo, at para sa mga team ng ecommerce na bumuo ng kumpletong katalogo ng larawan ng produkto (mga variant, eksena, at anggulo) mula sa isang solong pinagmulan na larawan.
Mas mura na ng 20% ang image input at output sa GPT Image 1.5 kumpara sa GPT Image 1, kaya mas marami kang magagawang at maiuulit na imahe sa parehong badyet..
Pwede mong subukan ang bagong modelo sa OpenAI Playground(magbubukas sa bagong window) o basahin ang gabay sa prompt(magbubukas sa bagong window) para sa inspirasyon.
Gumagamit na ng GPT Image 1.5 ang mga negosyo at startup sa iba't ibang industriya kabilang ang mga malikhaing tool, e-commerce, marketing software, at marami pang iba. Nasasabik kaming ibahagi ang ilan sa mga halimbawang ito sa ibaba.
Bago
Nakaraan
“Mas mura na ngayon ng 20% ang image input at output sa GPT Image 1.5 kumpara sa GPT Image 1, kaya maaari kang bumuo at mag-iterate ng mas maraming imahe gamit ang parehong budget. Ang mga resulta ay malinis, makatotohanan, at maaasahan, na sumusuporta sa mas mabilis na daloy ng trabaho mula konsepto hanggang produksyon sa mga platform tulad ng Wix. Batay sa aming pagsubok at sa mga pangunahing kaso ng paggamit na nakikita namin sa Wix, ang pagkakapare-pareho at kalidad ay nagtatagisan upang gawin itong isa sa mga pangunahing modelo ng pagbuo ng larawan ngayon.
— Hila Gat, Head ng AI Research at Data Science sa Wix
Ang bagong ChatGPT Images ay inilulunsad na ngayon sa lahat ng mga user ng ChatGPT at mga user ng API sa buong mundo sa iba't ibang mga surface. Gumagana ito sa iba't ibang mga modelo, kaya hindi mo kailangang pumili ng kahit ano para magamit ito.
Naniniwala kami na nasa simula pa lang kami ng kung ano ang maaaring i-enable ng image generation. Muling umusad ang modelo sa text rendering, na may kakayahang humawak ng mas siksik at mas maliliit na text.
May-akda
Contributors
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, Bing Liang, Boyuan Chen, Charlie Nash, David Medina, Dibya Bhattacharjee, Jianfeng Wang, Kenji Hata, Kiwhan Song, Mengchao Zhong, Mike Starr, Yuguang Yang
Research Contributors
Bram Wallace, Dmytro Okhonko, Haitang Hu, Kshitij Gupta, Li Jing, Lu Liu, Peter Zhokhov, Qiming Yuan, Senthil Purushwalkam, Yizhen Zhang
Core Inference
Adam Tart, Alyssa Huang, Andrew Braunstein, Jane Park, Karen Li, Tomer Kaftan
Research Collaborators
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
Inference Collaborators
Jiayu Bai, Kevin King, Stanley Hsieh, Weiyi Zheng
Data & Evaluation
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
Applied
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
Safety, Safety Systems, Integrity, Policy & Trust
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
Product Operations, Program Management and Governance
Antonio Di Francesco, Filippo Raso, Grace Wu, Josh Metherd, Ruth Costigan
Legal
Ally Bennett, Tony Song, Tyce Walters
Communications, Marketing, Community, Design & Creative
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
Special Thanks
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
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
