I dag lancerer vi en ny version af ChatGPT Images drevet af vores nye flagskibsmodel til billedgenerering. Uanset om du skaber noget fra bunden eller redigerer et foto, vil du nu få det resultat, du forestiller dig. Den laver præcise redigeringer, mens den bevarer detaljer, som folks udseende, intakte, og genererer billeder op til 4 gange hurtigere. Samtidig introducerer vi en ny funktion til billeder i ChatGPT designet til at gøre billedgenerering sjovt – for at inspirere og gøre kreativ udforskning nemt
Den nye billedmodel- og funktion rulles ud i dag i ChatGPT for alle brugere og i API'en som GPT‑image‑1.5.
Når du beder om redigeringer af et uploadet billede, følger modellen nu din hensigt mere pålideligt—ned til de små detaljer—og ændrer kun det, du beder om, mens den holder elementer som belysning, komposition og folks udseende konsistente i forskelligt input, output og efterfølgende redigeringer.
Dette låser op for resultater, der matcher din hensigt—mere nyttige fotoredigeringer, mere troværdige tøj- og frisureprøver sammen med stilistiske filtre og konceptuelle transformationer, der bevarer essensen af det originale billede. Sammen betyder disse forbedringer, at ChatGPT kan fungere som et kreativt studie i din lomme, der kan udføre praktiske redigeringer og udtryksfulde gengivelser.
Modellen udmærker sig i forskellige typer redigering – herunder tilføjelse, subtraktion, kombination, blanding og transponering – så du får de ændringer, du ønsker, uden at miste det, der gør billedet specielt.
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.
Modellens kreativitet skinner igennem transformationer, der ændrer og tilføjer elementer—som tekst og layout—for at føre idéer ud i livet samtidig med, at vigtige detaljer bevares. Disse transformationer fungerer både for simple og mere indviklede koncepter og er nemme at afprøve ved hjælp af forudindstillede stilarter og ideer i den nye funktion ChatGPT Images(åbner i et nyt vindue)—ingen skriftlig forespørgsel er påkrævet.
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.
Modellen følger instruktioner mere pålideligt end vores første version. Dette muliggør mere præcise redigeringer samt mere indviklede originale kompositioner, hvor forholdene mellem elementerne bevares som tilsigtet.
Ny
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
Forrige
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
Modellen tager endnu et skridt fremad inden for tekstgengivelse og kan håndtere tættere og mindre 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.
Modellen forbedrer også ekstra dimensioner, der fører til mere umiddelbart brugbare resultater, som f.eks. gengivelse af mange små ansigter, og hvordan naturlige resultater ser ud.
Ny
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…
Forrige
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…
Ud over at generere billeder ved at beskrive, hvad du gerne vil se i en besked, introducerer vi en dedikeret sektion for billeder(åbner i et nyt vindue) i ChatGPT—tilgængelig i sidemenuen via mobilappen og på chatgpt.com—for at gøre det hurtigere og nemmere at udforske og afprøve billeder. Det omfatter snesevis af forudindstillede filtre og forespørgsler til at kickstarte inspiration, som regelmæssigt opdateres for at afspejle nye tendenser.
Sammen giver disse opgraderinger dig mulighed for at skabe billeder, der bedre matcher din vision, fra små ændringer til fulde nyfortolkninger.
Denne model strømliner virksomhedsarbejdsgange med hurtigere billedgenerering, præcis redigering og ensartede visuelle detaljer på tværs af iterationer. Teams kan udforske idéer, lave målrettede ændringer og visualisere komplekse eller tørre koncepter, som understøtter brugercases inden for markedsføring, design, e-handel og intern kommunikation.
Vi kørte mange af eksemplerne fra vores første lancering af billedgenerering igen for at evaluere præstationen. Modellen viser tydelige forbedringer af flere forskellige tilfælde, selvom resultaterne stadig er ufuldkomne. Selvom denne udgivelse repræsenterer meningsfulde fremskridt, er der stadig betydelig plads til forbedring i fremtidige iterationer.
Ny
create a poster of deep sea creatures at different depths, with a vertical ocean cutaway, styled in a beautiful japanese detailed anime style
Forrige
create a poster of deep sea creatures at different depths, with a vertical ocean cutaway, styled in a beautiful japanese detailed anime style
Der er stadig nogle videnskabelige unøjagtigheder, men ~70 % er korrekt, og grafikken er meget mere levende, så du undgår for tidlig beskæring.
gpt-image-1.5 i API'en leverer alle de samme forbedringer i ChatGPT Images: Den er bedre til billedbevaring- og redigering end GPT Image 1.
Du vil se en mere konsekvent bevarelse af brandede logoer og vigtige visuelle elementer af flere redigeringer—der gør den velegnet til markedsførings- og brandarbejde som grafik- og logoskabelse samt for e-handelshold, der genererer komplette produktbilledkataloger (varianter, scener og vinkler) fra et enkelt kildebillede.
Billedinput og -output er nu 20 % billigere i GPT Image 1.5 sammenlignet med GPT Image 1, så du kan generere og gentage på flere billeder for det samme budget.
Du kan prøve den nye model i OpenAI Playground(åbner i et nyt vindue) eller læse forespørgselsvejledning(åbner i et nyt vindue) for inspiration.
Virksomheder og startups i flere forskellige brancher, herunder kreative værktøjer, e-handel, markedsføringssoftware m.m., bruger allerede GPT Image 1.5. Vi er spændte på at dele nogle af disse eksempler nedenfor.
Ny
Forrige
“GPT Image 1.5 genererer billeder i høj kvalitet, hvor den overholder forespørgslen og bevarer komposition, belysning og fine detaljer. Resultaterne er rene, realistiske og pålidelige, hvilket understøtter hurtigere koncept-til-produktionsarbejdsgange på platforme som Wix. Baseret på vores test og de vigtigste brugercases, vi ser hos Wix, konkurrerer konsistensen og kvaliteten om at gøre det til en af de førende billedgenereringsmodeller i dag.
— Hila Gat, chef for AI-forskning og datavidenskab hos Wix
Den nye ChatGPT Images udrulles nu til alle ChatGPT‑brugere og API-brugere globalt i dag på flere platforme. Den fungerer i flere modeller, så du behøver ikke vælge noget for at bruge den.
Vi mener, at vi stadig er i begyndelsen af, hvad billedgenerering kan muliggøre. Dagens opdatering er et meningsfuldt skridt fremad med mere i vente fra finere redigeringer til rigere, mere detaljerede output på flere sprog.
Skrevet af
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
