#GPT-4o says it can't create images

1 messages · Page 1 of 1 (latest)

night totem
#

ChatGPT shared link: (optional)

Steps to reproduce:

I asked it to create an image of a person overlooking a balcony

Expected result:

The image via DALL-E

Actual result:

It says it can't create images

Additional information

Browser: Chrome
OS: MacOS

cobalt kelpBOT
#
Thank you for reporting a bug related to DALL·E.

If relevant and not already provided, we recommend adding a link to the associated ChatGPT conversation and uploading any relevant images here for easier troubleshooting.

night totem
heavy cliff
#

The image generation capabilities of GPT-4o are not yet released.

cedar dawn
heavy cliff
# cedar dawn thats bull. I use it all the time.

Okay.

I mean you don't. GPT-4o is still calling dalle-3 to generate images.

From their release page,

Today we are publicly releasing text and image inputs and text outputs. Over the upcoming weeks and months, we’ll be working on the technical infrastructure, usability via post-training, and safety necessary to release the other modalities.

So, no, the native, multimodal, image-generation capabilities of gpt-4o are not publicly available at this time.

cedar dawn
#

yes but thats not the issue acecord is having. their issue is that it wont even use dalle

#

@night totem is this for new chats too?

heavy cliff
#

The OP could very well have some custom instructions which are interfering because their prompt seems to work fine.