Danas objavljujemo novu verziju ChatGPT Images, koju pokreće naš novi vodeći model za generiranje slika. Sad, bez obzira stvarate li od nule ili uređujete fotografiju, dobit ćete rezultat kakav ste zamislili. Omogućuje precizne izmjene uz očuvanje detalja, poput izgleda osoba, i generira slike do 4x brže. Uz to uvodimo i novu značajku Images unutar ChatGPT‑a, osmišljenu kako bi generiranje slika bilo sjajno iskustvo koje će potaknuti inspiraciju i učiniti kreativno istraživanje jednostavnim
Novi model Images i nova značajka danas se postupno uvode u ChatGPT za sve korisnike, a u API kao gpt-image-1.5.
Sad, kad zatražite izmjene na prenesenoj slici, model se pouzdanije drži vaše namjere – sve do sitnih detalja – mijenjajući samo ono što tražite, dok elementi poput osvjetljenja, kompozicije i izgleda osoba ostaju dosljedni kroz ulaze, izlaze i naknadne izmjene.
To otvara mogućnost rezultata koji doista odgovaraju vašoj namjeri – korisnijih uređivanja fotografija, uvjerljivijih isprobavanja odjeće i frizura, kao i stilskih filtara i konceptualnih transformacija koje zadržavaju bit izvornog prizora. Zajedno, ova poboljšanja znače da ChatGPT može djelovati kao kreativni studio u vašem džepu, sposoban i za praktične izmjene i za kreativna preoblikovanja.
Model se ističe u različitim vrstama uređivanja – uključujući dodavanje, uklanjanje, kombiniranje, stapanje i premještanje – pa dobivate željene izmjene bez gubitka onoga što sliku čini posebnom.
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.
Kreativnost modela dolazi do izražaja kroz transformacije koje mijenjaju i dodaju elemente – poput teksta i izgleda – kako bi ideje oživjele, dok važni detalji ostaju sačuvani. Ove transformacije djeluju i za jednostavne i za složenije pojmove, a lako ih je isprobati koristeći unaprijed postavljene stilove i ideje u novoj značajci ChatGPT Images(otvara se u novom prozoru) – nije potreban pisani upit.
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.
U odnosu na našu početnu verziju, ovaj model pouzdanije slijedi upute. To omogućuje preciznije uređivanje kao i složenije originalne kompozicije, gdje su odnosi između elemenata očuvani kako je zamišljeno.
Novo
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
Prethodni model
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 čini još jedan iskorak u prikazu teksta te može pouzdano obrađivati gušći i sitniji tekst.
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 također poboljšava dodatne dimenzije koje rezultiraju neposredno upotrebljivijim ishodima, poput prikaza brojnih manjih lica i prirodnog izgleda rezultata.
Novo
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…
Prethodni model
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…
Uz generiranje slika opisivanjem onoga što želite vidjeti u poruci, uvodimo i posebno mjesto za slike(otvara se u novom prozoru) u ChatGPT‑u – dostupno u bočnoj traci putem mobilne aplikacije i na chatgpt.com – kako bismo istraživanje i isprobavanje slika učinili bržim i jednostavnijim. Uključuje desetke unaprijed postavljenih filtara i upita koji potiču inspiraciju, a redovito se ažuriraju kako bi odražavali nove trendove.
Zajedno vam ova poboljšanja omogućuju da stvorite slike koje bolje odgovaraju vašoj viziji, od malih izmjena do potpunih preinaka.
Ovaj model pojednostavljuje tijekove rada bržim generiranjem slika, preciznim izmjenama i dosljednim vizualnim detaljima kroz više izmjena. Timovi mogu istraživati ideje, uvoditi ciljane promjene i vizualizirati složene ili „suhe“ koncepte, čime se podržavaju slučajevi primjene u marketingu, dizajnu, e-trgovini i internim komunikacijama.
Ponovno smo pokrenuli mnoge primjere iz našeg početnog lansiranja generiranja slika kako bismo procijenili učinkovitost. Model pokazuje jasna poboljšanja u nizu slučajeva, iako rezultati i dalje nisu savršeni. Premda ovo izdanje predstavlja značajan napredak, i dalje ima mnogo prostora za poboljšanja u budućim verzijama.
Novo
create a poster of deep sea creatures at different depths, with a vertical ocean cutaway, styled in a beautiful japanese detailed anime style
Prethodni model
create a poster of deep sea creatures at different depths, with a vertical ocean cutaway, styled in a beautiful japanese detailed anime style
Još uvijek postoje neke znanstvene netočnosti, ali oko 70 % je točno i grafika je znatno živopisnija, uz izbjegavanje prerane obrade ruba slike.
gpt-image-1.5 u API-ju donosi sva ista poboljšanja kao ChatGPT Images: snažniji je u očuvanju slike i uređivanju u odnosu na GPT Image 1.
Tijekom izmjena model dosljedno čuva logotipe i ključne vizualne elemente brendova, što ga čini posebno prikladnim za marketinške potrebe i vizualni identitet, poput izrade grafika i logotipa, kao i za timove u e-trgovini koji iz jedne izvorne slike izrađuju cjelovite kataloge proizvoda s različitim varijantama, scenama i kutovima.
Ulazi i izlazi slika sad su 20 % jeftiniji u GPT Image 1.5 u usporedbi s GPT Image 1, pa za isti budžet možete generirati i doraditi više slika.
Novi model možete isprobati u OpenAI Playgroundu(otvara se u novom prozoru) ili pročitati vodič za upite(otvara se u novom prozoru) kako biste se nadahnuli.
Tvrtke i startupi iz različitih sektora, uključujući kreativne alate, e-trgovinu, marketinški softver i druge, već koriste GPT Image 1.5. U nastavku s veseljem dijelimo neke od tih primjera.
Novo
Prethodni model
„GPT Image 1.5 generira slike visoke vjernosti i vjerno prati zadani opis, pritom čuvajući kompoziciju, osvjetljenje i fine detalje. Rezultati su čisti, realistični i pouzdani te podržavaju brže tijekove rada od koncepta do produkcije na platformama poput Wixa. Na temelju naših testiranja i glavnih slučajeva primjene koje vidimo u Wixu, dosljednost i kvaliteta ističu ga kao jedan od vodećih modela za generiranje slika danas.”
– Hila Gat, voditeljica odjela za istraživanje umjetne inteligencije i podatkovnu znanost, Wix
Novi ChatGPT Images danas se globalno uvodi za sve korisnike ChatGPT‑a i API-ja na svim sučeljima. Radi u svim modelima, pa ne morate ništa posebno odabrati kako biste ga koristili.
Vjerujemo da smo još uvijek na početku onoga što može omogućiti generiranje slika. Današnje ažuriranje je značajan korak naprijed, s još više poboljšanja koja uvodimo – od preciznijih izmjena do bogatijih i detaljnijih rezultata na različitim jezicima.
Autor
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
