Illum, qed noħorġu verżjoni ġdida ta’ ChatGPT Images(jinfetaħ f’tieqa ġdida), imħaddma mill-mudell ewlieni l-ġdid tagħna tal-ġenerazzjoni tal-immaġnijiet. Issa, kemm jekk qed toħloq xi ħaġa mill-bidu jew teditja ritratt, se tikseb ir-riżultat li qed timmaġina. Jagħmel edits preċiżi filwaqt li jżomm id-dettalji intatti, u jiġġenera immaġnijiet sa 4x aktar malajr. Flimkien ma’ dan, qed nintroduċu funzjoni Images(jinfetaħ f’tieqa ġdida) ġdida fi ħdan ChatGPT, iddisinjata biex tagħmel il-ġenerazzjoni tal-immaġnijiet pjaċevoli—biex tqajjem l-ispirazzjoni u tagħmel l-esplorazzjoni kreattiva bla sforz.
Il-mudell il-ġdid ta’ Images qed jibda jitħaddem illum f’ChatGPT għall-utenti kollha, u huwa disponibbli fl-API bħala GPT Image 1.5. L-esperjenza l-ġdida ta’ Images f’ChatGPT qed tibda titħaddem ukoll illum għall-biċċa l-kbira tal-utenti, bl-aċċess għal Business u Enterprise jasal aktar tard.
Issa, meta titlob edits għal immaġni mtellgħa, il-mudell iżomm mal-intenzjoni tiegħek b’mod aktar affidabbli—sal-iżgħar dettalji—u jibdel biss dak li titlob filwaqt li jżomm elementi bħad-dawl, il-kompożizzjoni u d-dehra tan-nies konsistenti bejn l-inputs, l-outputs u l-edits sussegwenti.
Dan jiftaħ riżultati li jaqblu mal-intenzjoni tiegħek—edits tar-ritratti aktar utli, try-ons ta’ ħwejjeġ u hairstyles aktar kredibbli, flimkien ma’ filtri stilistiċi u trasformazzjonijiet kunċettwali li jżommu l-essenza tal-immaġni oriġinali. Flimkien, dawn it-titjibiet ifissru li ChatGPT jista’ jaġixxi bħala studio kreattiv fil-but tiegħek, kapaċi kemm għal edits prattiċi kif ukoll għal immaġinazzjonijiet mill-ġdid espressivi.
Il-mudell jeċċella f’tipi differenti ta’ editjar—inklużi żieda, tnaqqis, kombinazzjoni, taħlit u traspożizzjoni—biex tikseb il-bidliet li trid mingħajr ma titlef dak li jagħmel l-immaġni speċjali.
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.
Il-kreattività tal-mudell tidher fit-trasformazzjonijiet li jbiddlu u jżidu elementi—bħat-test u t-tqassim—biex jagħtu l-ħajja lill-ideat, filwaqt li jżommu dettalji importanti. Dawn it-trasformazzjonijiet jaħdmu kemm għal kunċetti sempliċi kif ukoll għal oħrajn aktar kumplessi, u huma faċli biex tipprovahom billi tuża stili u ideat preset fil-funzjoni l-ġdida ChatGPT Images(jinfetaħ f’tieqa ġdida)—mingħajr il-ħtieġa ta’ prompt miktub.
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.
Il-mudell isegwi l-istruzzjonijiet b’mod aktar affidabbli mill-verżjoni inizjali tagħna. Dan jippermetti edits aktar preċiżi kif ukoll kompożizzjonijiet oriġinali aktar kumplessi, fejn ir-relazzjonijiet bejn l-elementi jinżammu kif maħsub.
Ġdid
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
Preċedenti
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
Il-mudell jagħmel pass ieħor ’il quddiem fir-renderjar tat-test, u kapaċi jimmaniġġja test aktar dens u iżgħar.
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.
Il-mudell itejjeb ukoll dimensjonijiet addizzjonali li jittraduċu f’outputs aktar immedjatament użabbli, bħar-renderjar ta’ ħafna uċuħ żgħar u kemm l-outputs jidhru naturali.
Ġdid
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…
Preċedenti
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…
Minbarra li tiġġenera immaġnijiet billi tiddeskrivi dak li tixtieq tara f’messaġġ, qed nintroduċu post iddedikat għal Images(jinfetaħ f’tieqa ġdida) f’ChatGPT—disponibbli fis-sidebar permezz tal-app mobbli u fuq chatgpt.com—biex nagħmlu l-esplorazzjoni u l-prova ta’ immaġnijiet aktar veloċi u eħfef. Dan jinkludi għexieren ta’ filtri u prompts preset biex jagħtu bidu għall-ispirazzjoni, aġġornati regolarment biex jirriflettu xejriet emerġenti.
Flimkien, dawn l-aġġornamenti jħalluk toħloq immaġnijiet li jaqblu aħjar mal-viżjoni tiegħek, minn edits żgħar sa immaġinazzjonijiet mill-ġdid sħaħ.
Erġajna għaddejna minn ħafna mill-eżempji mit-tnedija inizjali tagħna tal-ġenerazzjoni tal-immaġnijiet biex nevalwaw il-prestazzjoni. Il-mudell juri titjib ċar f’firxa ta’ każijiet, għalkemm ir-riżultati għadhom mhumiex perfetti. Filwaqt li din ir-rilaxx tirrappreżenta progress sinifikanti, għad hemm spazju konsiderevoli għal titjib f’iterazzjonijiet futuri.
Ġdid
create a poster of deep sea creatures at different depths, with a vertical ocean cutaway, styled in a beautiful japanese detailed anime style
Preċedenti
create a poster of deep sea creatures at different depths, with a vertical ocean cutaway, styled in a beautiful japanese detailed anime style
Għad hemm xi ineżattezzi xjentifiċi, iżda madwar 70% korrett u grafika ħafna aktar ħajja, tevita qtugħ kmieni wisq.
GPT Image 1.5 fl-API(jinfetaħ f’tieqa ġdida) jagħti l-istess titjibiet kollha bħal ChatGPT Images: huwa aktar b’saħħtu fil-preservazzjoni u l-editjar tal-immaġnijiet minn GPT Image 1.
Se tara preservazzjoni aktar konsistenti ta’ logos ta’ marki u viżwali ewlenin bejn edits, u dan jagħmlu adattat ħafna għal xogħol ta’ marketing u marka bħal grafika u ħolqien ta’ logos, u għal timijiet tal-ecommerce li jiġġeneraw katalgi sħaħ ta’ immaġnijiet ta’ prodotti (varjanti, xeni u angoli) minn immaġni ta’ sors wieħed.
L-inputs u l-outputs tal-immaġnijiet issa huma 20% orħos f’GPT Image 1.5 meta mqabbla ma’ GPT Image 1, biex tkun tista’ tiġġenera u ttenni fuq aktar immaġnijiet bl-istess baġit.
Tista’ tipprova l-mudell il-ġdid fil-OpenAI Playground(jinfetaħ f’tieqa ġdida), tara l-gallerija(jinfetaħ f’tieqa ġdida), jew taqra l-gwida tal-prompt(jinfetaħ f’tieqa ġdida) għall-ispirazzjoni.
Intrapriżi u startups f’diversi industriji, inklużi għodod kreattivi, e-commerce, software tal-marketing u aktar, diġà qed jużaw GPT Image 1.5.
Ġdid
Preċedenti
“GPT Image 1.5 jiġġenera immaġnijiet ta’ fedeltà għolja b’aderenza qawwija mal-prompt, filwaqt li jżomm il-kompożizzjoni, id-dawl u d-dettall fin. Ir-riżultati huma nodfa, realistiċi u affidabbli, u jappoġġjaw flussi ta’ xogħol aktar veloċi mill-kunċett sal-produzzjoni fuq pjattaformi bħal Wix. Abbażi tat-testijiet tagħna u tal-każijiet ewlenin ta’ użu li naraw f’Wix, il-konsistenza u l-kwalità jagħmluh wieħed mill-mudelli ewlenin tal-ġenerazzjoni tal-immaġnijiet illum.”
— Hila Gat, Kap tar-Riċerka fl-AI u tax-Data Science f’Wix
Il-mudell il-ġdid ChatGPT Images(jinfetaħ f’tieqa ġdida) qed jibda jitħaddem issa għall-utenti kollha ta’ ChatGPT u tal-API globalment illum fuq il-pjattaformi kollha. Jaħdem fuq il-mudelli kollha, għalhekk m’għandekx bżonn tagħżel xejn biex tużah. Il-verżjoni ta’ ChatGPT Images li tnediet aktar kmieni din is-sena se tibqa’ disponibbli għall-utenti kollha bħala GPT personalizzat(jinfetaħ f’tieqa ġdida).
Aħna nemmnu li għadna biss fil-bidu ta’ dak li tista’ tippermetti l-ġenerazzjoni tal-immaġnijiet. L-aġġornament tal-lum huwa pass sinifikanti ’l quddiem b’aktar li ġej, minn edits aktar fini sa outputs aktar sinjuri u dettaljati f’diversi lingwi.
Awtur
Kontributuri
Tmexxija tal-Proġett
Gabriel Goh — Kap tar-Riċerka
Adele Li — Kap tal-Prodott
Bill Peebles — Kap ta’ Sora
Aditya Ramesh — Kap tas-Simulazzjoni tad-Dinja
Mark Chen — Uffiċjal Kap tar-Riċerka
Prafulla Dhariwal — Kap tal-Multimodalità
Tim Ewlieni
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
Kontributuri għar-Riċerka
Bram Wallace, Dmytro Okhonko, Haitang Hu, Kshitij Gupta, Li Jing, Lu Liu, Peter Zhokhov, Qiming Yuan, Senthil Purushwalkam, Yizhen Zhang
Inferenza Ewlenija
Adam Tart, Alyssa Huang, Andrew Braunstein, Jane Park, Karen Li, Tomer Kaftan
Kollaboraturi tar-Riċerka
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
Kollaboraturi tal-Inferenza
Jiayu Bai, Kevin King, Stanley Hsieh, Weiyi Zheng
Data & Evalwazzjoni
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
Applikat
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
Sikurezza, Sistemi ta’ Sikurezza, Integrità, Politika & Fiduċja
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
Operazzjonijiet tal-Prodott, Ġestjoni tal-Programm u Governanza
Antonio Di Francesco, Filippo Raso, Grace Wu, Josh Metherd, Ruth Costigan
Legali
Ally Bennett, Tony Song, Tyce Walters
Komunikazzjonijiet, Marketing, Komunità, Disinn & Kreattività
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
Ringrazzjamenti Speċjali
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
Eżekuttiv
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
