Hacker News Viewer

OpenAI Livestream: ChatGPT Images 2.0

by wahnfrieden on 4/21/2026, 6:50:00 PM

https://openai.com/live/

Comments

by: hahahacorn

One of the images in the blog (<a href="https:&#x2F;&#x2F;images.ctfassets.net&#x2F;kftzwdyauwt9&#x2F;4d5dizAOajLfAXkGZ74DJh&#x2F;f3c89f754604050c0980a0bc9de2091c&#x2F;images-2-cornell.png?w=3840&amp;q=90&amp;fm=webp" rel="nofollow">https:&#x2F;&#x2F;images.ctfassets.net&#x2F;kftzwdyauwt9&#x2F;4d5dizAOajLfAXkGZ7...</a>) is a carbon copy of an image from an article posted Mar 27, 2026 with credits given to an individual: <a href="https:&#x2F;&#x2F;www.cornellsun.com&#x2F;article&#x2F;2026&#x2F;03&#x2F;cornell-accepts-5-776-students-to-class-of-2030" rel="nofollow">https:&#x2F;&#x2F;www.cornellsun.com&#x2F;article&#x2F;2026&#x2F;03&#x2F;cornell-accepts-5...</a><p>Was this an oversight? Or did their new image generation model generate an image that was essentially a copy of an existing image?

4/21/2026, 8:13:29 PM


by: simonw

I&#x27;ve been trying out the new model like this:<p><pre><code> OPENAI_API_KEY=&quot;$(llm keys get openai)&quot; \ uv run https:&#x2F;&#x2F;tools.simonwillison.net&#x2F;python&#x2F;openai_image.py \ -m gpt-image-2 \ &quot;Do a where&#x27;s Waldo style image but it&#x27;s where is the raccoon holding a ham radio&quot; </code></pre> Code here: <a href="https:&#x2F;&#x2F;github.com&#x2F;simonw&#x2F;tools&#x2F;blob&#x2F;main&#x2F;python&#x2F;openai_image.py" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;simonw&#x2F;tools&#x2F;blob&#x2F;main&#x2F;python&#x2F;openai_imag...</a><p>Here&#x27;s what I got from that prompt. I do not think it included a raccoon holding a ham radio (though the problem with Where&#x27;s Waldo tests is that I don&#x27;t have the patience to solve them for sure): <a href="https:&#x2F;&#x2F;gist.github.com&#x2F;simonw&#x2F;88eecc65698a725d8a9c1c918478ac41?permalink_comment_id=6112150#gistcomment-6112150" rel="nofollow">https:&#x2F;&#x2F;gist.github.com&#x2F;simonw&#x2F;88eecc65698a725d8a9c1c918478a...</a>

4/21/2026, 7:26:48 PM


by: minimaxir

HN submission for a direct link to the product announcement which for some reason is being penalized by the HN algorithm: <a href="https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=47853000">https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=47853000</a>

4/21/2026, 7:17:53 PM


by: simonw

Suggest renaming this to &quot;OpenAI Livestream: ChatGPT Images 2.0&quot;

4/21/2026, 7:43:22 PM


by: volkk

the guys presenting are probably all like 25x smarter than I am but good god, literally 0 on screen presence or personality.

4/21/2026, 7:53:25 PM


by: ____tom____

No mention of modifying existing images, which is more important than anything they mentioned.<p>I think we all know the feeling of getting an image that is ok, but needs a few modifications, and being absolutely unable to get the changes made.<p>It either keeps coming up with the same image, or gives you a completely new take on the image with fresh problems.<p>Anyone know if modification of existing images is any better?<p>Anything better that OpenAI?

4/21/2026, 7:58:23 PM


by: dktp

One interesting thing I found comparing OpenAI and Gemini image editing is - Gemini rejects anything involving a well known person. Anything. OpenAI is happy to edit and change every time I tried<p>I have a sideproject where I want to display standup comedies. I thought I could edit standup comedy posters with some AI to fit my design. Gemini straight up refuses to change any image of any standup comedy poster involving a well know human. OpenAI does not care and is happy to edit away

4/21/2026, 8:13:39 PM


by: bensyverson

I caught the last minute of this—was it just ChatGPT Images 2.0?

4/21/2026, 7:22:50 PM


by: amunozo

This is not as exciting as previous models were, but it is incredibly good. I am starting to think that expressing thoughts in words clearly is probably the most important and general skill of the future.

4/21/2026, 8:03:44 PM


by: Melatonic

Can it generate anything high resolution at increased cost and time? Or is it always restricted?

4/21/2026, 8:21:05 PM


by: esafak

<a href="https:&#x2F;&#x2F;openai.com&#x2F;index&#x2F;introducing-chatgpt-images-2-0&#x2F;" rel="nofollow">https:&#x2F;&#x2F;openai.com&#x2F;index&#x2F;introducing-chatgpt-images-2-0&#x2F;</a>

4/21/2026, 7:32:42 PM


by: bitnovus

great obfuscation idea - hidden message on a grain of rice

4/21/2026, 7:21:15 PM


by: bitnovus

No gpt-5.5

4/21/2026, 7:22:28 PM


by: szmarczak

Wow, the difference between AI and non-AI images collapses. I hate the future where I won&#x27;t be able to tell the difference.

4/21/2026, 7:45:38 PM


by: rqa129

Can it generate Chibi figures to mask the oligarchy&#x27;s true intentions on Twitter and make them more relatable?

4/21/2026, 7:38:18 PM


by: sho_hn

In 5 years and 3 months between DALL-E and Images 2.0 we&#x27;ve managed to progress from exuberant excitement to jaded indifference.

4/21/2026, 7:49:37 PM


by: brianbest101

[dead]

4/21/2026, 7:35:15 PM


by: zb3

Image generation? Hmm, would be cool if OpenAI also made a video-generation model someday..

4/21/2026, 7:24:22 PM


by: aliljet

I am hopeful that OpenAI will potentially offer clarity on their loss-leading subscription model. I&#x27;d prefer to know the real cost of a token from OpenAI as opposed to praying the venture-funded tokens will always be this cheap.

4/21/2026, 7:21:21 PM