Dibya Bhattacharjee

25 posts

Dibya Bhattacharjee

Dibya Bhattacharjee

@dibyayB

researcher @openai, imagegen

San Francisco, CA Katılım Ekim 2016
147 Takip Edilen250 Takipçiler
Dibya Bhattacharjee retweetledi
Justin Schroeder
Justin Schroeder@jpschroeder·
what. what. what. gpt-image-2 almost passes the pelican test...in a screenshot of a code editor.
Justin Schroeder tweet mediaJustin Schroeder tweet media
English
47
79
1.8K
115.7K
Dibya Bhattacharjee
@jasperdevs The best way to prompt our model can be quite different from nanobanana. For more photorealism, please try just adding "photorealistic" to your prompt (example generation with a simpler version of the original prompt below):
Dibya Bhattacharjee tweet media
English
0
1
6
108
Dibya Bhattacharjee retweetledi
Riley Goodside
Riley Goodside@goodside·
"School worksheet with maze, 32 wide by 48 tall, rows and columns numbered, no unreachable rooms, solution in blue pen, name field reads 'ChatGPT Images 2.0' in cursive at top" Note the fusion of code and imagegen this task requires.
Riley Goodside tweet media
English
16
15
358
22.5K
Dibya Bhattacharjee retweetledi
Bartosz Naskręcki
Bartosz Naskręcki@nasqret·
With the new ChatGPT Images 2.0, text-to-image generation finally feels like a true programming experience. I was part of the ChatGPT Pro Community early testing group. From my perspective as a research mathematician, this new model is a huge boost to imagination, allowing me, with just a few words, to sketch, draw, plan, and visualize intuitions that I previously could only keep in my head. The model is blazing fast, highly steerable, and extremely responsive to suggestions and changes. I am attaching a small gallery of recent experiments I conducted during the testing phase. Program your thinking to make the magic happen - now imagination is the only real limit.
Bartosz Naskręcki tweet mediaBartosz Naskręcki tweet mediaBartosz Naskręcki tweet mediaBartosz Naskręcki tweet media
English
4
6
96
4.2K
Dibya Bhattacharjee retweetledi
Dibya Bhattacharjee
Excited to finally be able to share what I've been working on recently! This was undoubtedly some of the most fun research I've ever done- can't wait to see what the community creates with this magical model
OpenAI@OpenAI

Introducing ChatGPT Images 2.0 A state-of-the-art image model that can take on complex visual tasks and produce precise, immediately usable visuals, with sharper editing, richer layouts, and thinking-level intelligence. Video made with ChatGPT Images

English
1
0
18
468
Dibya Bhattacharjee retweetledi
prinz
prinz@deredleritt3r·
The reasoning model is absolutely incredible. Here is what it generated (in one shot) in response to the prompt: "Please make an image setting forth a guide for how a utilization review entity should comply with the Texas laws governing use of AI in utilization review." The model found the Texas laws, reasoned through them, and generated an actual one-page compliance guide. All information in this image is accurate and correct. The model correctly deduced the "KEY RULE" and made it the most prominent text in the entire image. Texas laws are silent on whether "scheduling/routing" and "document management" are permitted use cases for AI in utilization review, but the model believes they should be permitted based on the statute - I agree. (2/4)
prinz tweet media
English
1
6
27
2.1K
Dibya Bhattacharjee retweetledi
Arena.ai
Arena.ai@arena·
Exciting news - GPT-Image-2 by @OpenAI has claimed the #1 spot across all Image Arena leaderboards! A clean sweep with a record-breaking +242 point lead in Text-to-Image - the largest gap we’ve seen to date. - #1 Text-to-Image (1512), +242 over #2 (Nano-banana-2 with web-search aka gemini-3.1-flash-image) - #1 Single-Image Edit (1513), +125 over #2 (Nano-banana-pro aka gemini-3-pro-image) - #1 Multi-Image Edit (1464), +90 over #2 (Nano-banana-2) No model has dominated Image Arena with margins this wide. Huge congratulations to @OpenAI on this major breakthrough in image generation! More performance breakdowns by category in the thread below.
Arena.ai tweet media
OpenAI@OpenAI

Made with ChatGPT Images 2.0

English
125
472
4.1K
888.8K
Dibya Bhattacharjee retweetledi
OpenAI
OpenAI@OpenAI·
Introducing ChatGPT Images 2.0 A state-of-the-art image model that can take on complex visual tasks and produce precise, immediately usable visuals, with sharper editing, richer layouts, and thinking-level intelligence. Video made with ChatGPT Images
English
686
1.7K
15.3K
2.1M
Dibya Bhattacharjee retweetledi
Angel 🌼
Angel 🌼@Angaisb_·
SO SO SO SO COOL GPT IMAGE 2 IS AMAZING
English
6
4
163
3.4K
Dibya Bhattacharjee retweetledi
Adele Li
Adele Li@adele__li·
Introducing ChatGPT Images 2.0 A new generation of image creation: sharper details, stronger visual composition, cleaner text rendering, and more control from idea to final asset openai.com/introducing-ch…
Adele Li tweet media
English
8
5
109
5.7K
Dibya Bhattacharjee retweetledi
OpenAI
OpenAI@OpenAI·
Thinking… Generating… Livestreaming… openai.com/live/
English
210
152
2.3K
223.9K