Diseembar 16, 2025

ChatGPT Images-ka cusub waa yimid

This post covers an image-generation launch.

For the current experience:

Soo kacaya…

Maanta, waxaan sii deynaynaa nooc cusub oo ah ChatGPT Images⁠(ku furmaa daaqad cusub), oo ku shaqaynaya noocayaga cusub ee hormuudka u ah soo saarida sawirka. Hadda, haddii aad wax ka samaynayso eber ama aad tafatirayso sawir, waxaad heli doontaa natiijada aad maskaxda ku hayso. Waxay samaysaa tafatir sax ah iyadoo faahfaahinta la ilaalinayo, waxayna soo saartaa sawirro ilaa 4x ka dhakhso badan. Sidoo kale, waxaan soo bandhigaynaa astaan Images⁠(ku furmaa daaqad cusub) cusub oo ku dhex jirta ChatGPT, oo loo naqshadeeyay inay soo saarista sawirka ka dhigto mid farxad leh—si ay u dhaliso dhiirrigelin oo ay u fududeyso sahminta hal-abuurka.

Nooca cusub ee Images maanta waxa uu ka bilaabmayaa ChatGPT dhammaan isticmaaleyaasha, wuxuuna ka diyaar yahay API-ga sida GPT Image 1.5. Khibradda cusub ee Images ee ChatGPT sidoo kale maanta ayay u bilaabmaysaa inta badan isticmaaleyaasha, halka gelitaanka Business iyo Enterprise uu iman doono goor dambe.

Tafatir sax ah oo ilaalinaya waxa muhiimka ah

Hadda, marka aad codsato in wax laga beddelo sawir la soo geliyay, noocku si ka sii kalsooni badan ayuu ugu hoggaansamaa ujeeddadaada—ilaa faahfaahinta yaryar—wuxuuna beddelaa oo keliya waxa aad codsato isagoo ilaalinaya walxo ay ka mid yihiin iftiinka, isku-dhiska, iyo muuqaalka dadka si ay isugu ekaadaan gelinnada, soo-saarka, iyo tafatirrada xiga.

Tani waxay furaysaa natiijooyin la jaanqaadaya ujeeddadaada—tafatirro sawir oo waxtar badan leh, tijaabooyin dhar iyo timo-jaris oo aad loo rumaysan karo, iyo sidoo kale filtarro qaabaysan iyo beddello fikradeed oo haya nuxurka sawirka asalka ah. Isku darka hagaajinnadan waxay ka dhigan tahay in ChatGPT uu noqon karo istuudiyo hal-abuur oo jeebkaaga ku jira, kana shaqayn kara tafatirro waxtar leh iyo dib-u-male-awaallo muujin leh labadaba.

Tafatirid

Noocku waxa uu ku fiican yahay noocyo kala duwan oo tafatir ah—oo ay ku jiraan ku darid, ka jarid, isku darka, milmidda, iyo kala wareejin—si aad u hesho isbeddellada aad rabto adigoon lumin waxa sawirka gaarka ka dhigaya.

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.

Beddello hal-abuur leh

Hal-abuurka noocku wuxuu ka dhex iftiimaa isbeddellada beddela oo ku dara walxo—sida qoraal iyo qaab-dhismeed—si fikradaha nolol loogu siiyo, iyadoo weli la ilaalinayo faahfaahinta muhiimka ah. Isbeddelladani waxay u shaqeeyaan fikrado fudud iyo kuwa aad u murugsanba, waana sahlan tahay in la tijaabiyo iyadoo la adeegsanayo qaabab iyo fikrado hore loo dejiyay oo ku jira astaanta cusub ee ChatGPT Images⁠(ku furmaa daaqad cusub)—looma baahna weydiin qoran.

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.

Raacidda tilmaamaha

Noocku wuxuu u raacaa tilmaamaha si ka kalsooni badan noocii hore ee bilowga ahaa. Tani waxay suuragelinaysaa tafatirro sax ah iyo sidoo kale isku-dhisyada asalka ah ee ka sii murugsan, halkaas oo xiriirrada u dhexeeya walxaha loo ilaaliyo sida loogu talagalay.

Cusub

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

Hore

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

Muujinta qoraalka

Noocku wuxuu qaadayaa tallaabo kale oo horumar ah oo ku saabsan muujinta qoraalka, isagoo awood u leh inuu maareeyo qoraal ka cufan oo ka yar.

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.

Hagaajinno tayo oo dheeraad ah

Noocku sidoo kale wuxuu hagaajiyaa dhinacyo dheeraad ah oo u turjumaya natiijooyin si degdeg ah loo isticmaali karo, sida soo saarista wajiyo yaryar oo badan iyo sida dabiiciga ah ee natiijooyinku u muuqdaan.

Cusub

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…

Hore

Goob cusub oo abuuris

Marka laga soo tago soo saarista sawirro adigoo farriin ku sharxaya waxa aad rabto inaad aragto, waxaan ChatGPT ku soo kordhinaynaa meel u gaar ah oo loogu talagalay Images⁠(ku furmaa daaqad cusub)—taas oo laga heli karo dhinaca app-ka moobilka iyo chatgpt.com—si sahminta iyo tijaabinta sawirradu u noqdaan kuwo ka dhakhso badan oo ka fudud. Waxay ka kooban tahay daraasiin filtarrro iyo weydiinno hore loo dejiyay si ay u kiciyaan dhiirrigelinta, kuwaas oo si joogto ah loo cusboonaysiiyo si ay uga tarjumaan isbeddellada soo baxaya.

Isku darka casriyeyntan waxay kuu oggolaanayaan inaad abuurto sawirro si fiican ugu dhow aragtidaada, laga bilaabo tafatirro yar yar ilaa dib-u-male-awaallo buuxa.

Hagaajinnada iyo xaddidaadaha

Waxaan dib u wadnay tusaalooyin badan oo ka mid ahaa daahfurkeennii hore ee soo saarista sawirka si aan u qiimeyno waxqabadka. Noocku wuxuu muujinayaa horumar cad xaalado kala duwan, inkastoo natiijooyinku aysan weli kaamil ahayn. In kasta oo sii-deyntani ay tahay horumar macno leh, haddana weli waxaa jira meel weyn oo lagu sii hagaajin karo wareegyada mustaqbalka.

Cusub

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

Hore

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

Weli waxaa jira khaladaad cilmiyeed qaar, laakiin qiyaastii 70% waa sax, garaafyaduna aad bay u muuqaal firfircoon yihiin, waxayna ka fogaataa goyn degdeg ah.

GPT Image 1.5 ee API-ga

GPT Image 1.5 ee API-ga⁠(ku furmaa daaqad cusub) wuxuu bixiyaa isla hagaajinnadii ay bixisay ChatGPT Images: wuxuu kaga fiican yahay ilaalinta iyo tafatirka sawirka marka loo eego GPT Image 1.

Waxaad arki doontaa ilaalin aad u joogto badan oo ku saabsan astaamaha sumadda leh iyo muuqaallada muhiimka ah inta lagu jiro tafatirrada, taasoo ka dhigaysa mid si fiican ugu habboon suuq-geynta iyo shaqada summadaha sida garaafyada iyo samaynta astaamaha, iyo sidoo kale kooxaha ecommerce-ka ee soo saaraya buugag sawirro alaabeed oo dhammaystiran (noocyo kala duwan, muuqaalado, iyo xaglo) iyagoo ka duulaya hal sawir oo keliya.

Gelinnada iyo soo-saarrada sawirku hadda waxay 20% ka jaban yihiin GPT Image 1.5 marka loo eego GPT Image 1, sidaas darteed waxaad ku soo saari kartaa oo aad ku celcelin kartaa sawirro badan isla miisaaniyaddaas.

Waxaad ku tijaabin kartaa nooca cusub OpenAI Playground⁠(ku furmaa daaqad cusub), ka daalacan kartaa gallery⁠(ku furmaa daaqad cusub), ama akhrin kartaa hagaha weydiinaha⁠(ku furmaa daaqad cusub) si aad dhiirrigelin u hesho.

Shirkado waaweyn iyo kuwa bilow ah oo ka kala socda warshado kala duwan, oo ay ku jiraan qalabka hal-abuurka, ganacsiga elektaroonigga ah, software-ka suuq-geynta, iyo kuwo kale, ayaa durba adeegsanaya GPT Image 1.5.

Cusub

Hore

“GPT Image 1.5 waxay soo saartaa sawirro aad u tayo sarreeya iyadoo si adag ugu hoggaansanta weydiinaha, isla markaana ilaalinaysa isku-dhiska, iftiinka, iyo faahfaahinta heerka hoose. Natiijooyinku waa nadiif, dhab-u-eg, oo la isku hallayn karo, taasoo taageerta socodka shaqo ee ka bilaabma fikrad ilaa wax-soo-saar si ka dhakhso badan, gaar ahaan madallo sida Wix. Marka laga eego tijaabooyinkeenna iyo kiisaska ugu waaweyn ee adeegsiga ee aan ku aragno Wix, joogtaynta iyo tayadu waxay ka dhigayaan mid ka mid ah noocyada soo saarista sawirka ee hormuudka ah maanta.”

— Hila Gat, Madaxa Cilmi-baarista AI iyo Cilmiga Xogta ee Wix

Helitaan

Nooca cusub ee ChatGPT Images⁠(ku furmaa daaqad cusub) ayaa hadda loo sii deynayaa dhammaan isticmaaleyaasha ChatGPT iyo isticmaaleyaasha API-ga adduunka oo dhan maanta dhammaan meelaha laga isticmaalo. Wuxuu ka shaqeeyaa noocyo kala duwan, sidaa darteed uma baahnid inaad wax doorato si aad u isticmaasho. Nooca ChatGPT Images ee la bilaabay horaantii sannadkan wuxuu sii ahaan doonaa mid dhammaan isticmaaleyaashu heli karaan isagoo ah GPT gaar ah⁠(ku furmaa daaqad cusub).

Waxaan aaminsanahay inaan weli joogno bilowga waxa soo saarida sawirku suurtagelin karto. Cusboonaysiinta maanta waa tallaabo macno leh oo hore loo qaaday, iyadoo wax badan ay weli soo socdaan, laga bilaabo tafatirro heer-hoose oo ka sii faahfaahsan ilaa natiijooyin ka sii qani ah oo faahfaahsan oo luuqado kala duwan ah.

2025

Qoraa

OpenAI

Ka qayb-qaatayaasha

Hoggaanka Mashruuca

Gabriel Goh — Hoggaamiyaha Cilmi-baarista

Adele Li — Hoggaamiyaha Alaabta

Bill Peebles — Hoggaamiyaha Sora

Aditya Ramesh — Hoggaamiyaha World Simulation

Mark Chen — Sarkaalka Sare ee Cilmi-baarista

Prafulla Dhariwal — Hoggaamiyaha Multimodal

Kooxda Muhiimka ah

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

Ka qayb-qaateyaasha Cilmi-baarista

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

Inference-ka Muhiimka ah

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

La-shaqeeyayaasha Cilmi-baarista

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

La-shaqeeyayaasha Inference-ka

Jiayu Bai, Kevin King, Stanley Hsieh, Weiyi Zheng

Xogta & Qiimaynta

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

Hirgelin

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

Badbaado, Nidaamyada Badbaadada, Hufnaan, Siyaasad & Kalsooni

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

Hawlaha Alaabta, Maareynta Barnaamijka iyo Maamul-wanaagga

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

Sharciga

Ally Bennett, Tony Song, Tyce Walters

Isgaarsiinta, Suuq-geynta, Bulshada, Naqshadeynta & Hal-abuurka

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

Mahadnaq Gaar ah

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

Maamulka Sare

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

Sii wad akhrinta

Eeg dhamaan

Soo bandhigida GPT-5.2

BadeecadDis 11, 2025

Sora 2 waa yimid

Cilmi-baarisSeb 30, 2025

Soo bandhigida Soo Saarida Sawirka 4o

BadeecadMar 25, 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