16. децембар 2025.

Novi ChatGPT Images je stigao

This post covers an image-generation launch.

For the current experience:

Учитавање…

Danas objavljujemo novu verziju ChatGPT Images⁠(отвара се у новом прозору), koju pokreće naš novi vodeći model za генерисање слика. Sada, bilo da kreirate nešto od nule ili uređujete fotografiju, dobićete rezultat kakav zamišljate. Omogućava precizne izmene uz očuvanje detalja i generiše slike do 4x brže. Uz to uvodimo i novu funkciju Images⁠(отвара се у новом прозору) u okviru ChatGPT‑a, osmišljenu da učini генерисање слика prijatnim — da podstakne inspiraciju i olakša kreativno istraživanje.

Novi Images model od danas postepeno stiže u ChatGPT svim korisnicima, a dostupan je i u API-ju kao GPT Image 1.5. Novo Images iskustvo u ChatGPT‑u takođe od danas postepeno stiže većini korisnika, dok će pristup za Business i Enterprise doći kasnije.

Precizne izmene koje čuvaju ono što je važno

Sada, kada zatražite izmene otpremljene slike, model pouzdanije prati vašu nameru — sve do sitnih detalja — menjajući samo ono što tražite, uz očuvanje elemenata kao što su osvetljenje, kompozicija i izgled ljudi doslednim kroz ulaze, izlaze i naknadne izmene.

To otključava rezultate koji odgovaraju vašoj nameri — korisnije izmene fotografija, uverljivije isprobavanje odeće i frizura, kao i stilske filtere i konceptualne transformacije koje zadržavaju suštinu originalne slike. Zajedno, ova poboljšanja znače da ChatGPT može da deluje kao kreativni studio u vašem džepu, sposoban i za praktične izmene i za izražajna preosmišljavanja.

Uređivanje

Model se ističe u različitim vrstama uređivanja — uključujući dodavanje, uklanjanje, kombinovanje, stapanje i premeštanje — tako da dobijete promene koje želite 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.

Kreativne transformacije

Kreativnost modela dolazi do izražaja kroz transformacije koje menjaju i dodaju elemente — poput teksta i rasporeda — kako bi ideje oživele, uz očuvanje važnih detalja. Ove transformacije funkcionišu i za jednostavne i za složenije koncepte, a lako ih je isprobati pomoću unapred podešenih stilova i ideja u novoj funkciji ChatGPT Images⁠(отвара се у новом прозору) — bez potrebe za pisanom instrukcijom.

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.

Praćenje instrukcija

Model pouzdanije prati instrukcije nego naša početna verzija. To omogućava preciznije izmene, kao i složenije originalne kompozicije, u kojima se odnosi između elemenata čuvaju onako 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

chatgpt-images-instruction-following-new

Prethodno

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

chatgpt-images-instruction-following-old

Prikazivanje teksta

Model pravi još jedan korak napred u prikazivanju teksta, sposoban da obradi 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

|---|---|---:|---:|

| 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.

Dodatna poboljšanja kvaliteta

Model se poboljšava i u dodatnim dimenzijama koje se prevode u odmah upotrebljivije rezultate, kao što su prikaz velikog broja malih lica i prirodnost 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…

Prethodno

Novi prostor za kreiranje

Pored generisanja slika opisivanjem onoga što želite da vidite u poruci, uvodimo i namenski prostor za Images⁠(отвара се у новом прозору) u ChatGPT‑u — dostupan u bočnoj traci kroz mobilnu aplikaciju i na chatgpt.com — kako bismo istraživanje i isprobavanje slika učinili bržim i lakšim. Uključuje desetine unapred podešenih filtera i instrukcija za brzi početak inspiracije, koji se redovno ažuriraju kako bi odražavali nove trendove.

Zajedno, ove nadogradnje vam omogućavaju da kreirate slike koje bolje odgovaraju vašoj viziji, od sitnih izmena do potpunih preosmišljavanja.

Poboljšanja i ograničenja

Ponovo smo pokrenuli mnoge primere iz našeg početnog lansiranja генерисања слика kako bismo procenili performanse. Model pokazuje jasna poboljšanja u nizu slučajeva, iako rezultati i dalje nisu savršeni. Iako ovo izdanje predstavlja značajan napredak, i dalje postoji mnogo prostora za poboljšanje u budućim iteracijama.

Novo

create a poster of deep sea creatures at different depths, with a vertical ocean cutaway, styled in a beautiful japanese detailed anime style

Prethodno

create a poster of deep sea creatures at different depths, with a vertical ocean cutaway, styled in a beautiful japanese detailed anime style

I dalje postoje neke naučne netačnosti, ali ~70% je tačno i grafika je mnogo živopisnija, uz izbegavanje preuranjenog odsecanja.

GPT Image 1.5 u API-ju

GPT Image 1.5 u API-ju⁠(отвара се у новом прозору) donosi sva ista poboljšanja kao ChatGPT Images: bolji je u očuvanju i uređivanju slika od GPT Image 1.

Videćete doslednije očuvanje brendiranih logotipa i ključnih vizuala kroz izmene, što ga čini veoma pogodnim za marketing i rad na brendu, poput grafike i kreiranja logotipa, kao i za e-trgovinske timove koji generišu kompletne kataloge slika proizvoda (varijante, scene i uglove) iz jedne izvorne slike.

Ulazi i izlazi slike sada su 20% jeftiniji u GPT Image 1.5 u poređenju sa GPT Image 1, tako da možete da generišete i iterirate nad više slika sa istim budžetom.

Novi model možete isprobati u OpenAI Playground-u⁠(отвара се у новом прозору), pregledati galeriju⁠(отвара се у новом прозору) ili pročitati vodič za instrukcije⁠(отвара се у новом прозору) za inspiraciju.

Preduzeća i startupi iz različitih industrija, uključujući kreativne alate, e-trgovinu, marketinški softver i druge, već koriste GPT Image 1.5.

Novo

Prethodno

„GPT Image 1.5 generiše slike visoke vernosti uz snažno praćenje instrukcija, čuvajući kompoziciju, osvetljenje i fine detalje. Rezultati su čisti, realistični i pouzdani, što omogućava brže tokove rada od koncepta do produkcije na platformama kao što je Wix. Na osnovu našeg testiranja i glavnih slučajeva upotrebe koje vidimo u Wix-u, doslednost i kvalitet ga svrstavaju među vodeće modele za генерисање слика danas.“

— Hila Gat, rukovodilac AI istraživanja i nauke o podacima u Wix-u

Dostupnost

Novi model ChatGPT Images⁠(отвара се у новом прозору) od danas se postepeno uvodi svim korisnicima ChatGPT‑a i API korisnicima širom sveta na svim površinama. Radi kroz modele, tako da ne morate ništa da birate da biste ga koristili. Verzija ChatGPT Images koja je lansirana ranije ove godine ostaće dostupna svim korisnicima kao prilagođeni GPT⁠(отвара се у новом прозору).

Verujemo da smo i dalje tek na početku onoga što генерисање слика može da omogući. Današnje ažuriranje predstavlja značajan korak napred, a tek dolazi još toga — od detaljnijih izmena do bogatijih i detaljnijih rezultata na različitim jezicima.

2025.

Аутор

OpenAI

Saradnici

Vođstvo projekta

Gabriel Goh — vođa istraživanja

Adele Li — vođa proizvoda

Bill Peebles — vođa za Sora

Aditya Ramesh — vođa simulacije sveta

Mark Chen — glavni direktor istraživanja

Prafulla Dhariwal — vođa multimodalnosti

Osnovni tim

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

Saradnici u istraživanju

Bram Wallace, Dmytro Okhonko, Haitang Hu, Kshitij Gupta, Li Jing, Lu Liu, Peter Zhokhov, Qiming Yuan, Senthil Purushwalkam, Yizhen Zhang

Osnovno zaključivanje

Adam Tart, Alyssa Huang, Andrew Braunstein, Jane Park, Karen Li, Tomer Kaftan

Saradnici na istraživanju

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

Saradnici na zaključivanju

Jiayu Bai, Kevin King, Stanley Hsieh, Weiyi Zheng

Podaci i evaluacija

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

Primena

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

Bezbednost, sistemi bezbednosti, integritet, politika i poverenje

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

Operacije proizvoda, upravljanje programima i upravljanje

Antonio Di Francesco, Filippo Raso, Grace Wu, Josh Metherd, Ruth Costigan

Pravni tim

Ally Bennett, Tony Song, Tyce Walters

Komunikacije, marketing, zajednica, dizajn i kreativni tim

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

Posebna zahvalnost

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

Rukovodstvo

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

Наставите са читањем

Прикажи све

Predstavljamo GPT-5.2

Производ11. дец 2025.

Sora 2 je stigla

Истраживање30. сеп 2025.

Представљамо 4o генерисање слика

Производ25. мар 2025.

Now change the article to the markdown below:

# Introducing GPT‑Image‑1.5

### *The new and improved ChatGPT Images*

**December 16, 2025**

---

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

### 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