Hi,
I just wanted to know if the API accepts image inputs to GPT-4, and if so, is there any documentation for using GPT-4 for a VQA or image captioning task.
Thank you
Hi,
I just wanted to know if the API accepts image inputs to GPT-4, and if so, is there any documentation for using GPT-4 for a VQA or image captioning task.
Thank you
GPT does not yet support image inputs, API or otherwise.
well yes and no it does support images but has been instructed not to for security reasons like there’s a lot of safety protocols to help legally protect the users and the compony… dont beleave me go look up "chatgpt ‘dam’ “do-anthing-man” videos