GPT Image
No written verdict yet. Here is what commenters said.
By version sentiment of people who named that release, latest release first
Versions with at least 5 people. 3 people didn't name a version. Small samples swing a lot, so read the counts too. Compare all models →
Why people recommend it
“Right now gpt-image-2 is better than my own model, and it services around ~96% of the requests in diffui.”
Show 3 more
“I use gpt image 2 very heavily for my current project (ai UI design tool).”
“it crushed every complex image comprehension benchmark I had”
Caveats and dissent
“Overall fixed some of the main issues / gripes I had with gpt-image-2”
Show 2 more
“their 4-panel comic strip using gpt-image-2 was an absolute mess too”
“It’s not a great look when the biggest proponents and supposed experts still manage to make such a royal botch job of things.”
Often compared with
Who recommends it in their own words
From the makers not counted in the ranking
“I built GPT Image 1.5 (https://gpt-image-15.com), a web interface”
Threads where it came up
- OpenAI Livestream 9 mentions
- ChatGPT Images 2.5 7 mentions
- GPT Image 1.5 7 mentions
- Qwen 3.0 Image Pro 3 mentions
- ChatGPT Images 2.0 3 mentions
- Show HN: Imagedojo.ai – Blind arena for Google, OpenAI, and xAI image generators 2 mentions
Also written as GPT Image 2, GPT Image 1.5, gpt-image-1, GPT-Image-2. Data: gpt-image.json. Quotes are verbatim; the verdict and theme labels are written by a model from these comments, and every clause links to its sources.
All comments 53
“the GPT-Image look will become blase from overuse”
“Here is the same prompt from GPT Image 2”
“comparing the outputs of gpt-image-2 and qwen 2.1”
“gpt-image-2 got it right every time.”
“albeit yellow-tinged as all hell”
“Right now gpt-image-2 is better than my own model, and it services around ~96% of the requests in diffui.”
“Overall fixed some of the main issues / gripes I had with gpt-image-2”
“I use gpt image 2 very heavily for my current project (ai UI design tool).”
“their 4-panel comic strip using gpt-image-2 was an absolute mess too”
“it crushed every complex image comprehension benchmark I had”
“the same prompt in GPT-Image-2 has no such issue”
“it's nowhere near gpt-image-2 at least for high density UI design”
“It’s easier to correct an issue like this than to deal with an image that simply doesn’t follow your prompt.”
“Looks like this model is meaningfully less good than gpt-image-2”
“Gpt-image-2 is a VERY capable designer”
“gpt-image-2 scored 12 out of 15”
“They must have trained on GPT Image 1 outputs.”
“You could also use a multimodal model such as gpt-image-2”
“Here's one I got from OpenAI's gpt-image-2 just the other day”
It’s a tough problem but Retro Diffusion is making some incredible progress https://retrodiffusion.ai/
“Proprietary? Either gpt-image-2 or NB2.”
“I remembering being absolutely shocked when the gpt-image series managed to pass the Labyrinth test”
“I highly recommend doing image->code as the flow here.”
Where did you get that info from? According to Google's own docs as well as my own image generation tests via the API, it supports up to 4K natively for gemini-3.1-flash-image-preview (aka NB2). It just defaults to 1K. But I didn't see anything in the docs stating that it's just a simple upscale for larger resolutions. https://ai.google.dev/gemini-api/docs/image-generation#generate-4k-images
“proprietary models like Gemini 3.1 Flash Image and GPT Image 2”
“Use it with 3D and a GPT Image 2 or Nano Banana Pro pass.”
“leveraging GPT-Image-2 for creating a comic book”
“But I will give GPT-Image-2 a try.”
“the gpt-image-2 drop really legitized the bet”
“It’s not a great look when the biggest proponents and supposed experts still manage to make such a royal botch job of things.”
“the results were surprisingly good as well”
“Gpt-Image in the editing benchmarks of my GenAI Showdown shot up from scoring 3/12 to 10/12.”
Fun stuff. Mythology is steeped in these chimera-type creatures, where we mix and match body parts from different animals to create new ones Mr. Potato head style. There’s a great Demetri Martin sketch about this, where he says: the horse becomes the majestic Pegasus, the lion becomes the griffin, and the hawk becomes... the double hawk. I've also used GenAI to visualize some of the creatures I've come up with as wel
“ask a editing model such as Nano Banana or GPT Image to remove that leg.”
“here's gpt-image-2 as a recent example”
“Now look at GPT Image 2 and Nano Banana Pro; those original nits are mostly a thing of the past.”
“gpt-image-2 has a lot more action, especially in the Apple Cart images.”
“One where Nano banana fails but gpt image 2 worked”
Cost me < 1 cents - https://elsrc.com/elsrc/waldo/wojak.jpg p.s. aaaand that's soft launch my SaaS above, you can replace wojak.jpg with anything you want and it will paint that. It's basically appending to prompt defined by elsrc's dashboard. Hopefully a more sane way to manage genai content. Be gentle to my server, hn!
“that is interesting cause I feel gpt-image-1 did have that feature.”
“gpt-image-1.5 was a big leap in visual quality”
“visually weak”
“until they finally pushed out gpt-image-1.5”
“The first is very fake and the second is a strong improvement”
“The best model I've found for this, that almost bakes in full ControlNet capability, is oddly gpt-image-1.5.”
“GPT-image-1 (and gpt-image-1.5) are outliers in their ability to generate images with a proper alpha channel.”
“GPT-image-1 (and gpt-image-1.5) are outliers in their ability to generate images with a proper alpha channel.”
“OAI's latest image model outperforms Google's in LMArena in both image generation and image editing.”
One other test you could add is generating a chessboard from a FEN. I was surprised to see NBP able to do that (however, it seems to only work with fewer pieces, after a certain amount it makes mistakes or even generates a completely wrong image) https://files.catbox.moe/uudsyt.png
“GPT-Image 1.5 is clearly a step up as an editing model, but it performed worse in purely generative tasks”
“dropping from 11 (out of 14) to 9”
“than gpt-image-1, doubling the previous score from 4/12 to 8/12”
“OpenAI’s gpt-image-1 for the raw image generation”